Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5459 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0180. Min Range: -4.0180
Max Act: 4.0180. Min Act: -0.1700
Data Index: 5526886 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.9867. Min Act: -0.1700
Data Index: 3170488 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.9555. Min Act: -0.1700
Data Index: 194463 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.9555. Min Act: -0.1700
Data Index: 6258231 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.9242. Min Act: -0.1700
Data Index: 1493100 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.9242. Min Act: -0.1700
Data Index: 8301792 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8929. Min Act: -0.1700
Data Index: 6233781 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8617. Min Act: -0.1700
Data Index: 2647267 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8617. Min Act: -0.1700
Data Index: 5531325 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8304. Min Act: -0.1700
Data Index: 634629 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8304. Min Act: -0.1700
Data Index: 3560910 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.8304. Min Act: -0.1700
Data Index: 4878941 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7679. Min Act: -0.1700
Data Index: 5996135 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7679. Min Act: -0.1700
Data Index: 6637553 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7991. Min Act: -0.1700
Data Index: 1162612 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7991. Min Act: -0.1700
Data Index: 8405429 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7679. Min Act: -0.1700
Data Index: 2674749 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7366. Min Act: -0.1700
Data Index: 2489664 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7366. Min Act: -0.1700
Data Index: 1991973 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0180. Min Range: -4.0180
Max Act: 3.7366. Min Act: -0.1700
Data Index: 653434 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19