Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0653. Min Range: -5.0653
Max Act: 5.0653. Min Act: -0.1700
Data Index: 3770563 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.9403. Min Act: -0.1700
Data Index: 3434610 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.7216. Min Act: -0.1700
Data Index: 1540032 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.6903. Min Act: -0.1700
Data Index: 6980723 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.6591. Min Act: -0.1700
Data Index: 2211778 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.6278. Min Act: -0.1700
Data Index: 3850821 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.6278. Min Act: -0.1700
Data Index: 8195166 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5653. Min Act: -0.1700
Data Index: 4852722 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5966. Min Act: -0.1700
Data Index: 4262003 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5966. Min Act: -0.1700
Data Index: 4585258 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5653. Min Act: -0.1700
Data Index: 5565765 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5653. Min Act: -0.1700
Data Index: 5580725 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5966. Min Act: -0.1700
Data Index: 7329571 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5966. Min Act: -0.1700
Data Index: 4198779 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5966. Min Act: -0.1700
Data Index: 756011 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5028. Min Act: -0.1700
Data Index: 1059861 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5028. Min Act: -0.1700
Data Index: 4121721 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5341. Min Act: -0.1700
Data Index: 4065324 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5341. Min Act: -0.1700
Data Index: 4066303 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0653. Min Range: -5.0653
Max Act: 4.5028. Min Act: -0.1700
Data Index: 6691436 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19