Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 11.1657. Min Range: -11.1657
Max Act: 11.1657. Min Act: -0.1700
Data Index: 959002 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1657. Min Range: -11.1657
Max Act: 11.1032. Min Act: -0.1700
Data Index: 1570199 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.9782. Min Act: -0.1700
Data Index: 1798162 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.9157. Min Act: -0.1700
Data Index: 6041054 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.8532. Min Act: -0.1700
Data Index: 277284 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.8532. Min Act: -0.1700
Data Index: 3559514 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.8532. Min Act: -0.1700
Data Index: 2127468 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7907. Min Act: -0.1700
Data Index: 1274710 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.8532. Min Act: -0.1700
Data Index: 7867459 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.8532. Min Act: -0.1700
Data Index: 6120847 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7907. Min Act: -0.1700
Data Index: 4068252 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 1268102 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 409631 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 2339435 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.6657. Min Act: -0.1700
Data Index: 6029057 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 848337 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 3765695 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7907. Min Act: -0.1700
Data Index: 8582018 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 5529191 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1657. Min Range: -11.1657
Max Act: 10.7282. Min Act: -0.1700
Data Index: 4746396 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19