Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1121 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7639. Min Act: -0.1700
Data Index: 3124422 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7514. Min Act: -0.1700
Data Index: 2421417 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7308. Min Act: -0.1700
Data Index: 3053902 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7308. Min Act: -0.1700
Data Index: 1623163 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7185. Min Act: -0.1700
Data Index: 4771459 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7226. Min Act: -0.1700
Data Index: 5620723 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7308. Min Act: -0.1700
Data Index: 6481506 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7267. Min Act: -0.1700
Data Index: 3865459 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7328. Min Act: -0.1700
Data Index: 336883 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7226. Min Act: -0.1700
Data Index: 3542470 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7267. Min Act: -0.1700
Data Index: 622012 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7103. Min Act: -0.1700
Data Index: 835450 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7328. Min Act: -0.1700
Data Index: 6239763 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7226. Min Act: -0.1700
Data Index: 915197 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7205. Min Act: -0.1700
Data Index: 4422665 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7185. Min Act: -0.1700
Data Index: 6637285 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7267. Min Act: -0.1700
Data Index: 2916592 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7226. Min Act: -0.1700
Data Index: 4469812 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7103. Min Act: -0.1700
Data Index: 6473670 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7639. Min Range: -0.7639
Max Act: 0.7123. Min Act: -0.1700
Data Index: 118008 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #19