Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 754 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.4411. Min Act: -0.1700
Data Index: 3176892 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.4411. Min Act: -0.1700
Data Index: 3961201 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.4411. Min Act: -0.1700
Data Index: 849186 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.2536. Min Act: -0.1700
Data Index: 8245785 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.1911. Min Act: -0.1700
Data Index: 4826669 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.0661. Min Act: -0.1700
Data Index: 3351730 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.0661. Min Act: -0.1700
Data Index: 8728987 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4411. Min Range: -9.4411
Max Act: 9.0036. Min Act: -0.1700
Data Index: 2837524 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.9411. Min Act: -0.1700
Data Index: 2610407 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.9411. Min Act: -0.1700
Data Index: 4747659 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.8786. Min Act: -0.1700
Data Index: 5772741 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.8786. Min Act: -0.1700
Data Index: 1813864 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.8161. Min Act: -0.1700
Data Index: 4784485 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.8161. Min Act: -0.1700
Data Index: 4738472 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.7536. Min Act: -0.1700
Data Index: 5885930 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.7536. Min Act: -0.1700
Data Index: 3947986 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.7536. Min Act: -0.1700
Data Index: 8216058 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.6911. Min Act: -0.1700
Data Index: 828834 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.7536. Min Act: -0.1700
Data Index: 606956 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4411. Min Range: -9.4411
Max Act: 8.7536. Min Act: -0.1700
Data Index: 7621090 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19