Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2220 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.6193. Min Act: -0.1700
Data Index: 2427090 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.5255. Min Act: -0.1700
Data Index: 8185533 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.5255. Min Act: -0.1700
Data Index: 817565 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.4943. Min Act: -0.1700
Data Index: 2761504 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.4318. Min Act: -0.1700
Data Index: 3965597 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.3380. Min Act: -0.1700
Data Index: 2156626 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.3380. Min Act: -0.1700
Data Index: 7993449 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.2755. Min Act: -0.1700
Data Index: 89765 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.2130. Min Act: -0.1700
Data Index: 6503221 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.2443. Min Act: -0.1700
Data Index: 5012877 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1818. Min Act: -0.1700
Data Index: 7552612 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1505. Min Act: -0.1700
Data Index: 7758800 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1193. Min Act: -0.1700
Data Index: 3080607 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1505. Min Act: -0.1700
Data Index: 2642169 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1505. Min Act: -0.1700
Data Index: 1756585 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1505. Min Act: -0.1700
Data Index: 8465335 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1193. Min Act: -0.1700
Data Index: 7392790 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.1193. Min Act: -0.1700
Data Index: 2644165 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.0880. Min Act: -0.1700
Data Index: 399320 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6193. Min Range: -5.6193
Max Act: 5.0880. Min Act: -0.1700
Data Index: 7499803 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #19