Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 97 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.2964. Min Act: -0.1700
Data Index: 3000250 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.2026. Min Act: -0.1700
Data Index: 1452788 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.2026. Min Act: -0.1700
Data Index: 4712497 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.2026. Min Act: -0.1700
Data Index: 8055850 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1714. Min Act: -0.1700
Data Index: 26577 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1714. Min Act: -0.1700
Data Index: 7575571 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1714. Min Act: -0.1700
Data Index: 2589925 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1401. Min Act: -0.1700
Data Index: 6368545 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1401. Min Act: -0.1700
Data Index: 440864 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1401. Min Act: -0.1700
Data Index: 4296678 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1714. Min Act: -0.1700
Data Index: 5583062 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1714. Min Act: -0.1700
Data Index: 7876561 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1088. Min Act: -0.1700
Data Index: 6721645 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1088. Min Act: -0.1700
Data Index: 643283 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1088. Min Act: -0.1700
Data Index: 7014224 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.1088. Min Act: -0.1700
Data Index: 6073776 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.0776. Min Act: -0.1700
Data Index: 3791028 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.0776. Min Act: -0.1700
Data Index: 198575 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.0776. Min Act: -0.1700
Data Index: 3924282 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2964. Min Range: -4.2964
Max Act: 4.0776. Min Act: -0.1700
Data Index: 763131 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19