Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4568 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.7316. Min Act: -0.1700
Data Index: 691020 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.7316. Min Act: -0.1700
Data Index: 7932764 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.7003. Min Act: -0.1700
Data Index: 4899145 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.7003. Min Act: -0.1700
Data Index: 3784601 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.6066. Min Act: -0.1700
Data Index: 2327822 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.6066. Min Act: -0.1700
Data Index: 1845995 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5753. Min Act: -0.1700
Data Index: 7098914 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 8539175 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 8830046 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 5077258 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 1889509 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 7283542 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 205624 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 1687808 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5128. Min Act: -0.1700
Data Index: 4038487 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.5441. Min Act: -0.1700
Data Index: 6477718 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.4503. Min Act: -0.1700
Data Index: 6519494 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.4503. Min Act: -0.1700
Data Index: 7784276 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.4503. Min Act: -0.1700
Data Index: 8075719 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7316. Min Range: -5.7316
Max Act: 5.4503. Min Act: -0.1700
Data Index: 741790 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19