Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3858 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.1210. Min Act: -0.1700
Data Index: 6339420 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0894. Min Act: -0.1700
Data Index: 4624751 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0737. Min Act: -0.1700
Data Index: 1775563 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 5313733 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 2770711 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 6190768 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 7740111 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 7994112 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 3311290 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 2028850 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 117513 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0579. Min Act: -0.1700
Data Index: 24106 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 5173965 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 5030365 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 5005892 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 4105430 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 4075948 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 3880605 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 3868635 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1210. Min Range: -3.1210
Max Act: 3.0421. Min Act: -0.1700
Data Index: 3784180 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19