Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4006. Min Range: -4.4006
Max Act: 4.4006. Min Act: -0.1700
Data Index: 7923075 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8720715 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.9005. Min Act: -0.1700
Data Index: 5291832 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 3213411 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 536317 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8215051 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 7583139 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 7240938 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3666531 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 5127908 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 6208439 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8692. Min Act: -0.1700
Data Index: 6475573 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 5070553 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 7254313 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 4933786 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.7754. Min Act: -0.1700
Data Index: 3765265 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3851398 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8067. Min Act: -0.1700
Data Index: 3611120 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8380. Min Act: -0.1700
Data Index: 3967151 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4006. Min Range: -4.4006
Max Act: 3.8067. Min Act: -0.1700
Data Index: 3574231 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19