Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1300 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.7049. Min Act: -0.1700
Data Index: 2605433 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.6736. Min Act: -0.1700
Data Index: 2263729 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.5799. Min Act: -0.1700
Data Index: 2259803 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.5799. Min Act: -0.1700
Data Index: 8168309 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.5174. Min Act: -0.1700
Data Index: 328962 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4861. Min Act: -0.1700
Data Index: 7290362 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4549. Min Act: -0.1700
Data Index: 6498204 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4861. Min Act: -0.1700
Data Index: 1325555 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4236. Min Act: -0.1700
Data Index: 5155543 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4236. Min Act: -0.1700
Data Index: 6039642 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4236. Min Act: -0.1700
Data Index: 7235727 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.4236. Min Act: -0.1700
Data Index: 1064570 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3924. Min Act: -0.1700
Data Index: 597809 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3924. Min Act: -0.1700
Data Index: 1877040 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3611. Min Act: -0.1700
Data Index: 6796234 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3611. Min Act: -0.1700
Data Index: 8812095 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3299. Min Act: -0.1700
Data Index: 601744 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.3299. Min Act: -0.1700
Data Index: 8736970 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.2986. Min Act: -0.1700
Data Index: 7282683 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7049. Min Range: -6.7049
Max Act: 6.2986. Min Act: -0.1700
Data Index: 4020038 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19