Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3581 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5954. Min Act: -0.1700
Data Index: 1741888 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5642. Min Act: -0.1700
Data Index: 6246944 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5329. Min Act: -0.1700
Data Index: 5387025 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5329. Min Act: -0.1700
Data Index: 1777574 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5329. Min Act: -0.1700
Data Index: 8360259 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5642. Min Act: -0.1700
Data Index: 8381126 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5017. Min Act: -0.1700
Data Index: 6093852 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5017. Min Act: -0.1700
Data Index: 2644075 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.5017. Min Act: -0.1700
Data Index: 2113470 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 2459051 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7063013 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 1743205 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 6281469 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 324799 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4392. Min Act: -0.1700
Data Index: 6186226 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 328088 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4392. Min Act: -0.1700
Data Index: 2322859 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4704. Min Act: -0.1700
Data Index: 7155557 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4079. Min Act: -0.1700
Data Index: 2504567 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5954. Min Range: -5.5954
Max Act: 5.4079. Min Act: -0.1700
Data Index: 4512823 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19