Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2351 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.1360. Min Act: -0.1700
Data Index: 597683 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.1048. Min Act: -0.1700
Data Index: 2480882 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0735. Min Act: -0.1700
Data Index: 1245326 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0735. Min Act: -0.1700
Data Index: 2688284 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0423. Min Act: -0.1700
Data Index: 7957995 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0423. Min Act: -0.1700
Data Index: 5742890 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0423. Min Act: -0.1700
Data Index: 4360252 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0110. Min Act: -0.1700
Data Index: 1471719 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1360. Min Range: -6.1360
Max Act: 6.0110. Min Act: -0.1700
Data Index: 5839269 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9798. Min Act: -0.1700
Data Index: 429653 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9798. Min Act: -0.1700
Data Index: 1219918 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9485. Min Act: -0.1700
Data Index: 7658790 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9485. Min Act: -0.1700
Data Index: 4841672 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9485. Min Act: -0.1700
Data Index: 5250771 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9798. Min Act: -0.1700
Data Index: 3402383 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9485. Min Act: -0.1700
Data Index: 1069348 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9173. Min Act: -0.1700
Data Index: 3257328 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8860. Min Act: -0.1700
Data Index: 3483396 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.9173. Min Act: -0.1700
Data Index: 4449847 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1360. Min Range: -6.1360
Max Act: 5.8860. Min Act: -0.1700
Data Index: 4958540 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19