Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.6392. Min Act: -0.1700
Data Index: 8178468 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.4205. Min Act: -0.1700
Data Index: 8455972 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.3892. Min Act: -0.1700
Data Index: 7709182 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.3267. Min Act: -0.1700
Data Index: 1406658 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.3267. Min Act: -0.1700
Data Index: 2211202 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2955. Min Act: -0.1700
Data Index: 4098486 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2955. Min Act: -0.1700
Data Index: 3204739 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2642. Min Act: -0.1700
Data Index: 5786756 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2330. Min Act: -0.1700
Data Index: 329593 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2330. Min Act: -0.1700
Data Index: 2132003 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2330. Min Act: -0.1700
Data Index: 8142348 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 3015573 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2330. Min Act: -0.1700
Data Index: 6344163 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2330. Min Act: -0.1700
Data Index: 4979392 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 2792419 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 8299594 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 2104954 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.1705. Min Act: -0.1700
Data Index: 2280052 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 5712330 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6392. Min Range: -4.6392
Max Act: 4.2017. Min Act: -0.1700
Data Index: 4578660 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19