Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5452 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.9130. Min Act: -0.1700
Data Index: 8229674 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.7880. Min Act: -0.1700
Data Index: 4089167 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.6943. Min Act: -0.1700
Data Index: 7435057 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.6630. Min Act: -0.1700
Data Index: 5942786 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.5068. Min Act: -0.1700
Data Index: 4345656 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.5068. Min Act: -0.1700
Data Index: 3132069 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4755. Min Act: -0.1700
Data Index: 37549 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4443. Min Act: -0.1700
Data Index: 5846913 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4443. Min Act: -0.1700
Data Index: 5325782 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4443. Min Act: -0.1700
Data Index: 1074324 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4130. Min Act: -0.1700
Data Index: 5702607 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4443. Min Act: -0.1700
Data Index: 4049959 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.4130. Min Act: -0.1700
Data Index: 1195877 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3818. Min Act: -0.1700
Data Index: 3183509 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3818. Min Act: -0.1700
Data Index: 2491801 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3505. Min Act: -0.1700
Data Index: 1441421 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3818. Min Act: -0.1700
Data Index: 507090 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3818. Min Act: -0.1700
Data Index: 5595547 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3818. Min Act: -0.1700
Data Index: 7977484 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9130. Min Range: -5.9130
Max Act: 5.3505. Min Act: -0.1700
Data Index: 7826517 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19