Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0764. Min Range: -8.0764
Max Act: 8.0764. Min Act: -0.1700
Data Index: 6525262 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0764. Min Range: -8.0764
Max Act: 8.0764. Min Act: -0.1700
Data Index: 8528000 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.8889. Min Act: -0.1700
Data Index: 5892362 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.6702. Min Act: -0.1700
Data Index: 7437124 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.6389. Min Act: -0.1700
Data Index: 1406362 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.5764. Min Act: -0.1700
Data Index: 5916381 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.5452. Min Act: -0.1700
Data Index: 7958877 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.5139. Min Act: -0.1700
Data Index: 7096583 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.4827. Min Act: -0.1700
Data Index: 5535789 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.4514. Min Act: -0.1700
Data Index: 4514365 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.4514. Min Act: -0.1700
Data Index: 5483705 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.4202. Min Act: -0.1700
Data Index: 1646971 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.3264. Min Act: -0.1700
Data Index: 25857 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2952. Min Act: -0.1700
Data Index: 7241806 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2327. Min Act: -0.1700
Data Index: 6922834 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2639. Min Act: -0.1700
Data Index: 6394060 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2639. Min Act: -0.1700
Data Index: 7958873 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2327. Min Act: -0.1700
Data Index: 8262990 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2327. Min Act: -0.1700
Data Index: 7082111 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0764. Min Range: -8.0764
Max Act: 7.2014. Min Act: -0.1700
Data Index: 1454200 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19