Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4275 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7862. Min Range: -5.7862
Max Act: 5.7862. Min Act: -0.1700
Data Index: 7659637 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7862. Min Range: -5.7862
Max Act: 5.3174. Min Act: -0.1700
Data Index: 7153015 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7862. Min Range: -5.7862
Max Act: 5.1612. Min Act: -0.1700
Data Index: 3121269 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7862. Min Range: -5.7862
Max Act: 5.1299. Min Act: -0.1700
Data Index: 2447420 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7862. Min Range: -5.7862
Max Act: 5.0049. Min Act: -0.1700
Data Index: 7026308 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.9737. Min Act: -0.1700
Data Index: 5516420 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.8799. Min Act: -0.1700
Data Index: 260875 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.8799. Min Act: -0.1700
Data Index: 1984157 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.8174. Min Act: -0.1700
Data Index: 5984264 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.7549. Min Act: -0.1700
Data Index: 2318434 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.7237. Min Act: -0.1700
Data Index: 7210550 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5512318 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6924. Min Act: -0.1700
Data Index: 5822042 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6924. Min Act: -0.1700
Data Index: 193063 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6299. Min Act: -0.1700
Data Index: 199036 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6612. Min Act: -0.1700
Data Index: 3319855 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6299. Min Act: -0.1700
Data Index: 7260391 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6299. Min Act: -0.1700
Data Index: 3528897 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6299. Min Act: -0.1700
Data Index: 7974477 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7862. Min Range: -5.7862
Max Act: 4.6299. Min Act: -0.1700
Data Index: 742952 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19