Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4625 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.6358. Min Act: -0.1700
Data Index: 920536 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.6046. Min Act: -0.1700
Data Index: 3159927 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.5733. Min Act: -0.1700
Data Index: 3804537 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.5108. Min Act: -0.1700
Data Index: 827533 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.5108. Min Act: -0.1700
Data Index: 3402213 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4483. Min Act: -0.1700
Data Index: 2111878 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4483. Min Act: -0.1700
Data Index: 2492381 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4483. Min Act: -0.1700
Data Index: 6569201 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4483. Min Act: -0.1700
Data Index: 422516 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4171. Min Act: -0.1700
Data Index: 1874184 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4171. Min Act: -0.1700
Data Index: 8617424 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4171. Min Act: -0.1700
Data Index: 6746126 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.4171. Min Act: -0.1700
Data Index: 2642388 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3233. Min Act: -0.1700
Data Index: 8280452 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3546. Min Act: -0.1700
Data Index: 3868060 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3546. Min Act: -0.1700
Data Index: 2017996 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3233. Min Act: -0.1700
Data Index: 6856711 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3233. Min Act: -0.1700
Data Index: 5830938 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3233. Min Act: -0.1700
Data Index: 3018964 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6358. Min Range: -4.6358
Max Act: 4.3233. Min Act: -0.1700
Data Index: 4989439 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19