Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.9755. Min Act: -0.1700
Data Index: 3489043 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6943. Min Act: -0.1700
Data Index: 890863 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.6005. Min Act: -0.1700
Data Index: 5037280 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.5693. Min Act: -0.1700
Data Index: 6782610 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.5693. Min Act: -0.1700
Data Index: 3505842 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.4755. Min Act: -0.1700
Data Index: 589562 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.4755. Min Act: -0.1700
Data Index: 2766464 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.4755. Min Act: -0.1700
Data Index: 6683000 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.4130. Min Act: -0.1700
Data Index: 3214767 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3818. Min Act: -0.1700
Data Index: 1497487 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3505. Min Act: -0.1700
Data Index: 904308 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3505. Min Act: -0.1700
Data Index: 6039849 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3818. Min Act: -0.1700
Data Index: 5040630 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3193. Min Act: -0.1700
Data Index: 385144 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.2880. Min Act: -0.1700
Data Index: 6793355 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.3193. Min Act: -0.1700
Data Index: 889735 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.2880. Min Act: -0.1700
Data Index: 5464373 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.2568. Min Act: -0.1700
Data Index: 8580558 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.2880. Min Act: -0.1700
Data Index: 4870444 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9755. Min Range: -6.9755
Max Act: 6.2880. Min Act: -0.1700
Data Index: 1567335 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #19