Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5944 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4128. Min Range: -7.4128
Max Act: 7.4128. Min Act: -0.1700
Data Index: 77990 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4128. Min Range: -7.4128
Max Act: 7.1628. Min Act: -0.1700
Data Index: 4824961 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4128. Min Range: -7.4128
Max Act: 7.0065. Min Act: -0.1700
Data Index: 7420304 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.9753. Min Act: -0.1700
Data Index: 8063216 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.9440. Min Act: -0.1700
Data Index: 4842072 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.9440. Min Act: -0.1700
Data Index: 4460332 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.9440. Min Act: -0.1700
Data Index: 7318291 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.8503. Min Act: -0.1700
Data Index: 1653307 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7878. Min Act: -0.1700
Data Index: 671663 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7878. Min Act: -0.1700
Data Index: 313465 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7565. Min Act: -0.1700
Data Index: 2269570 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7565. Min Act: -0.1700
Data Index: 3153398 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3619510 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.7253. Min Act: -0.1700
Data Index: 1785975 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6628. Min Act: -0.1700
Data Index: 3664982 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6940. Min Act: -0.1700
Data Index: 1726960 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6628. Min Act: -0.1700
Data Index: 522656 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6315. Min Act: -0.1700
Data Index: 5755872 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6315. Min Act: -0.1700
Data Index: 4098341 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4128. Min Range: -7.4128
Max Act: 6.6003. Min Act: -0.1700
Data Index: 5226627 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19