Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.9373. Min Act: -0.1700
Data Index: 4383480 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.9061. Min Act: -0.1700
Data Index: 34546 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.8748. Min Act: -0.1700
Data Index: 4019719 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.8748. Min Act: -0.1700
Data Index: 3156347 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.8748. Min Act: -0.1700
Data Index: 4408382 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.8123. Min Act: -0.1700
Data Index: 8496112 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.8436. Min Act: -0.1700
Data Index: 692099 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.7811. Min Act: -0.1700
Data Index: 6832812 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.7186. Min Act: -0.1700
Data Index: 6842013 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.7498. Min Act: -0.1700
Data Index: 2764760 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6873. Min Act: -0.1700
Data Index: 8767084 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6561. Min Act: -0.1700
Data Index: 635303 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6561. Min Act: -0.1700
Data Index: 2151669 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6561. Min Act: -0.1700
Data Index: 1984807 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6873. Min Act: -0.1700
Data Index: 7172285 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6248. Min Act: -0.1700
Data Index: 8823142 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.5936. Min Act: -0.1700
Data Index: 2270613 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6248. Min Act: -0.1700
Data Index: 5758624 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.6248. Min Act: -0.1700
Data Index: 8814721 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9373. Min Range: -5.9373
Max Act: 5.5936. Min Act: -0.1700
Data Index: 1239670 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19