Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.5730. Min Act: -0.1700
Data Index: 7984319 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.4792. Min Act: -0.1700
Data Index: 2299645 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.4167. Min Act: -0.1700
Data Index: 922394 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.2917. Min Act: -0.1700
Data Index: 4995677 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.2917. Min Act: -0.1700
Data Index: 3304889 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.2292. Min Act: -0.1700
Data Index: 7932402 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1980. Min Act: -0.1700
Data Index: 4976938 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1980. Min Act: -0.1700
Data Index: 485835 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1355. Min Act: -0.1700
Data Index: 2617008 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1355. Min Act: -0.1700
Data Index: 6406758 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1355. Min Act: -0.1700
Data Index: 6102607 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 2474424 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 1596115 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 3690335 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 5164675 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 4272410 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.1042. Min Act: -0.1700
Data Index: 5865879 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.0730. Min Act: -0.1700
Data Index: 6545223 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.0730. Min Act: -0.1700
Data Index: 941897 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5730. Min Range: -6.5730
Max Act: 6.0730. Min Act: -0.1700
Data Index: 1200078 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19