Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1806. Min Range: -6.1806
Max Act: 6.1806. Min Act: -0.1700
Data Index: 4866702 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.9931. Min Act: -0.1700
Data Index: 1252385 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1806. Min Range: -6.1806
Max Act: 6.0244. Min Act: -0.1700
Data Index: 1164340 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.9931. Min Act: -0.1700
Data Index: 5778638 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.8369. Min Act: -0.1700
Data Index: 2574107 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.8056. Min Act: -0.1700
Data Index: 948255 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.7431. Min Act: -0.1700
Data Index: 7160714 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.6494. Min Act: -0.1700
Data Index: 8032915 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.6494. Min Act: -0.1700
Data Index: 2157757 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 62571 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8493772 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 8819363 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5869. Min Act: -0.1700
Data Index: 2741339 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5869. Min Act: -0.1700
Data Index: 2521453 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5556. Min Act: -0.1700
Data Index: 5250332 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5556. Min Act: -0.1700
Data Index: 607039 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5244. Min Act: -0.1700
Data Index: 8223257 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5244. Min Act: -0.1700
Data Index: 1646045 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5244. Min Act: -0.1700
Data Index: 6717013 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1806. Min Range: -6.1806
Max Act: 5.5244. Min Act: -0.1700
Data Index: 1680144 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19