Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1462 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.9367. Min Act: -0.1700
Data Index: 6312876 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.8742. Min Act: -0.1700
Data Index: 6312890 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.6867. Min Act: -0.1700
Data Index: 1701768 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.5617. Min Act: -0.1700
Data Index: 4841027 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4992. Min Act: -0.1700
Data Index: 2043870 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4367. Min Act: -0.1700
Data Index: 50680 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4992. Min Act: -0.1700
Data Index: 3818032 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4055. Min Act: -0.1700
Data Index: 3818036 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4367. Min Act: -0.1700
Data Index: 8512425 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.4055. Min Act: -0.1700
Data Index: 6679342 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.2805. Min Act: -0.1700
Data Index: 6628279 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3430. Min Act: -0.1700
Data Index: 4701175 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3742. Min Act: -0.1700
Data Index: 4271241 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3742. Min Act: -0.1700
Data Index: 4530154 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3742. Min Act: -0.1700
Data Index: 7835497 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3430. Min Act: -0.1700
Data Index: 3128164 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3742. Min Act: -0.1700
Data Index: 7568975 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3430. Min Act: -0.1700
Data Index: 6506291 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3117. Min Act: -0.1700
Data Index: 4645967 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9367. Min Range: -6.9367
Max Act: 6.3117. Min Act: -0.1700
Data Index: 6537299 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19