Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6185 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.3660. Min Act: -0.1700
Data Index: 3943531 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.1785. Min Act: -0.1700
Data Index: 7140985 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.1473. Min Act: -0.1700
Data Index: 237100 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.1473. Min Act: -0.1700
Data Index: 136964 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0848. Min Act: -0.1700
Data Index: 292469 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0848. Min Act: -0.1700
Data Index: 7280957 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0223. Min Act: -0.1700
Data Index: 3600482 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0535. Min Act: -0.1700
Data Index: 5777560 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0535. Min Act: -0.1700
Data Index: 692701 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9910. Min Act: -0.1700
Data Index: 2180412 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3660. Min Range: -6.3660
Max Act: 6.0223. Min Act: -0.1700
Data Index: 4852107 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9910. Min Act: -0.1700
Data Index: 7985211 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9598. Min Act: -0.1700
Data Index: 4490001 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9910. Min Act: -0.1700
Data Index: 2875523 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9598. Min Act: -0.1700
Data Index: 5035263 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.9285. Min Act: -0.1700
Data Index: 6264151 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.8660. Min Act: -0.1700
Data Index: 1747929 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.8973. Min Act: -0.1700
Data Index: 6207564 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.8660. Min Act: -0.1700
Data Index: 2615946 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3660. Min Range: -6.3660
Max Act: 5.8348. Min Act: -0.1700
Data Index: 6304431 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #19