Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2412 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.8765. Min Act: -0.1700
Data Index: 5266748 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.6890. Min Act: -0.1700
Data Index: 4872648 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.3140. Min Act: -0.1700
Data Index: 5263672 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.2515. Min Act: -0.1700
Data Index: 1559489 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.2515. Min Act: -0.1700
Data Index: 39205 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.2202. Min Act: -0.1700
Data Index: 5766204 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.2202. Min Act: -0.1700
Data Index: 1014459 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.2202. Min Act: -0.1700
Data Index: 547820 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1577. Min Act: -0.1700
Data Index: 8210200 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1890. Min Act: -0.1700
Data Index: 1534388 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 5077994 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 59413 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 1652253 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.1265. Min Act: -0.1700
Data Index: 7681633 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0952. Min Act: -0.1700
Data Index: 997187 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0640. Min Act: -0.1700
Data Index: 3302848 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0327. Min Act: -0.1700
Data Index: 4288415 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0640. Min Act: -0.1700
Data Index: 5081251 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0327. Min Act: -0.1700
Data Index: 3787956 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8765. Min Range: -7.8765
Max Act: 7.0015. Min Act: -0.1700
Data Index: 1520969 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19