Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4358 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.8245. Min Act: -0.1700
Data Index: 3192061 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.6370. Min Act: -0.1700
Data Index: 4120304 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.5433. Min Act: -0.1700
Data Index: 7468428 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.5433. Min Act: -0.1700
Data Index: 396762 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.5120. Min Act: -0.1700
Data Index: 3341457 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 1957914 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 987562 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 8590431 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 8725452 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 7133947 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 5486409 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4808. Min Act: -0.1700
Data Index: 3843295 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4495. Min Act: -0.1700
Data Index: 911566 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4495. Min Act: -0.1700
Data Index: 6737696 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4183. Min Act: -0.1700
Data Index: 8710314 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4183. Min Act: -0.1700
Data Index: 565895 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4183. Min Act: -0.1700
Data Index: 6496093 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.3870. Min Act: -0.1700
Data Index: 2308053 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4183. Min Act: -0.1700
Data Index: 611579 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8245. Min Range: -5.8245
Max Act: 5.4183. Min Act: -0.1700
Data Index: 1375602 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19