Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1272 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0042. Min Range: -7.0042
Max Act: 7.0042. Min Act: -0.1700
Data Index: 7451249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.9417. Min Act: -0.1700
Data Index: 7732870 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.7855. Min Act: -0.1700
Data Index: 37950 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.6605. Min Act: -0.1700
Data Index: 4433522 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.6292. Min Act: -0.1700
Data Index: 4364836 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.5980. Min Act: -0.1700
Data Index: 8633887 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.5042. Min Act: -0.1700
Data Index: 1751147 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.5042. Min Act: -0.1700
Data Index: 3638575 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.5042. Min Act: -0.1700
Data Index: 4628559 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4730. Min Act: -0.1700
Data Index: 963006 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4417. Min Act: -0.1700
Data Index: 5171745 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4417. Min Act: -0.1700
Data Index: 2597506 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4417. Min Act: -0.1700
Data Index: 774119 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4105. Min Act: -0.1700
Data Index: 797287 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4105. Min Act: -0.1700
Data Index: 6900079 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.3792. Min Act: -0.1700
Data Index: 5451360 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.4105. Min Act: -0.1700
Data Index: 2759825 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.3480. Min Act: -0.1700
Data Index: 1697677 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.3480. Min Act: -0.1700
Data Index: 7214331 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0042. Min Range: -7.0042
Max Act: 6.3480. Min Act: -0.1700
Data Index: 3846064 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19