Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7957. Min Act: -0.1700
Data Index: 3419653 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7644. Min Act: -0.1700
Data Index: 7669705 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7644. Min Act: -0.1700
Data Index: 1176634 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7332. Min Act: -0.1700
Data Index: 8709119 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 166118 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6388071 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 8586381 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 3190114 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 5379710 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 2142815 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.7019. Min Act: -0.1700
Data Index: 1291995 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 5996377 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 2622549 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 6862582 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 4648142 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 4302030 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 1995461 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6394. Min Act: -0.1700
Data Index: 7809725 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6394. Min Act: -0.1700
Data Index: 8117262 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7957. Min Range: -5.7957
Max Act: 5.6707. Min Act: -0.1700
Data Index: 245003 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19