Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1467. Min Range: -8.1467
Max Act: 8.1467. Min Act: -0.1700
Data Index: 8006789 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1467. Min Range: -8.1467
Max Act: 8.1154. Min Act: -0.1700
Data Index: 6138896 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1467. Min Range: -8.1467
Max Act: 8.0529. Min Act: -0.1700
Data Index: 426608 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.9279. Min Act: -0.1700
Data Index: 7795102 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.8654. Min Act: -0.1700
Data Index: 2931641 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.7717. Min Act: -0.1700
Data Index: 2864928 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.7404. Min Act: -0.1700
Data Index: 2257855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.7404. Min Act: -0.1700
Data Index: 2682725 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.6467. Min Act: -0.1700
Data Index: 4179515 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5842. Min Act: -0.1700
Data Index: 6028717 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5842. Min Act: -0.1700
Data Index: 3326201 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5529. Min Act: -0.1700
Data Index: 4167004 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5217. Min Act: -0.1700
Data Index: 335770 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5217. Min Act: -0.1700
Data Index: 2796389 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.5217. Min Act: -0.1700
Data Index: 4184210 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.4592. Min Act: -0.1700
Data Index: 128593 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.4592. Min Act: -0.1700
Data Index: 1050831 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.4279. Min Act: -0.1700
Data Index: 7938433 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.4279. Min Act: -0.1700
Data Index: 2379138 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1467. Min Range: -8.1467
Max Act: 7.4279. Min Act: -0.1700
Data Index: 8526560 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19