Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.7523. Min Act: -0.1700
Data Index: 8001162 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.5335. Min Act: -0.1700
Data Index: 6721383 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.4710. Min Act: -0.1700
Data Index: 2568613 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.4398. Min Act: -0.1700
Data Index: 218783 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.1898. Min Act: -0.1700
Data Index: 4141707 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.1585. Min Act: -0.1700
Data Index: 4012371 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.1273. Min Act: -0.1700
Data Index: 4329232 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.1273. Min Act: -0.1700
Data Index: 5406859 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.0960. Min Act: -0.1700
Data Index: 3246348 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.0335. Min Act: -0.1700
Data Index: 2988348 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7523. Min Range: -6.7523
Max Act: 6.0335. Min Act: -0.1700
Data Index: 637652 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.9710. Min Act: -0.1700
Data Index: 3981444 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.9710. Min Act: -0.1700
Data Index: 1255049 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.9085. Min Act: -0.1700
Data Index: 7901483 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8773. Min Act: -0.1700
Data Index: 3245323 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8773. Min Act: -0.1700
Data Index: 1632940 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8773. Min Act: -0.1700
Data Index: 7501620 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8460. Min Act: -0.1700
Data Index: 8084340 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8148. Min Act: -0.1700
Data Index: 7563268 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7523. Min Range: -6.7523
Max Act: 5.8148. Min Act: -0.1700
Data Index: 204160 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19