Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5417 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.1085. Min Act: -0.1700
Data Index: 1244665 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.1085. Min Act: -0.1700
Data Index: 7283451 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.0147. Min Act: -0.1700
Data Index: 7084861 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9835. Min Act: -0.1700
Data Index: 290446 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1085. Min Range: -7.1085
Max Act: 7.0147. Min Act: -0.1700
Data Index: 7408838 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9835. Min Act: -0.1700
Data Index: 8036449 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9522. Min Act: -0.1700
Data Index: 6861977 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9522. Min Act: -0.1700
Data Index: 3814066 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.9210. Min Act: -0.1700
Data Index: 5230587 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8897. Min Act: -0.1700
Data Index: 4588352 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8897. Min Act: -0.1700
Data Index: 8513049 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8897. Min Act: -0.1700
Data Index: 5579563 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8585. Min Act: -0.1700
Data Index: 8756245 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8272. Min Act: -0.1700
Data Index: 8046629 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8585. Min Act: -0.1700
Data Index: 5376906 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.8585. Min Act: -0.1700
Data Index: 3791387 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7647. Min Act: -0.1700
Data Index: 2089496 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 680972 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7647. Min Act: -0.1700
Data Index: 7636149 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1085. Min Range: -7.1085
Max Act: 6.7960. Min Act: -0.1700
Data Index: 1005930 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19