Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3826 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1216. Min Range: -6.1216
Max Act: 6.1216. Min Act: -0.1700
Data Index: 4253897 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.7779. Min Act: -0.1700
Data Index: 4636422 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.8091. Min Act: -0.1700
Data Index: 8140934 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.7779. Min Act: -0.1700
Data Index: 6865588 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.7466. Min Act: -0.1700
Data Index: 5651671 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6841. Min Act: -0.1700
Data Index: 3466585 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6841. Min Act: -0.1700
Data Index: 1426026 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6216. Min Act: -0.1700
Data Index: 2333329 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6216. Min Act: -0.1700
Data Index: 4877771 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6529. Min Act: -0.1700
Data Index: 6508343 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6216. Min Act: -0.1700
Data Index: 1949181 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6216. Min Act: -0.1700
Data Index: 2441978 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.6529. Min Act: -0.1700
Data Index: 788745 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5904. Min Act: -0.1700
Data Index: 6154871 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5904. Min Act: -0.1700
Data Index: 4802095 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5591. Min Act: -0.1700
Data Index: 4743048 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5591. Min Act: -0.1700
Data Index: 6244350 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5279. Min Act: -0.1700
Data Index: 5532794 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5591. Min Act: -0.1700
Data Index: 2401009 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1216. Min Range: -6.1216
Max Act: 5.5279. Min Act: -0.1700
Data Index: 6390166 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #19