Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2527 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.2859. Min Act: -0.1700
Data Index: 1335407 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.2859. Min Act: -0.1700
Data Index: 8558276 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.2234. Min Act: -0.1700
Data Index: 2307171 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.2234. Min Act: -0.1700
Data Index: 6569023 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.0359. Min Act: -0.1700
Data Index: 3170404 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.0046. Min Act: -0.1700
Data Index: 4395226 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2859. Min Range: -8.2859
Max Act: 8.0046. Min Act: -0.1700
Data Index: 7791443 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.9109. Min Act: -0.1700
Data Index: 736289 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.9421. Min Act: -0.1700
Data Index: 2951652 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.9109. Min Act: -0.1700
Data Index: 5008653 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.8796. Min Act: -0.1700
Data Index: 2544890 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.7859. Min Act: -0.1700
Data Index: 1159045 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.7859. Min Act: -0.1700
Data Index: 2871916 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.7234. Min Act: -0.1700
Data Index: 5305775 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.7234. Min Act: -0.1700
Data Index: 2594228 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.7234. Min Act: -0.1700
Data Index: 7283053 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.6921. Min Act: -0.1700
Data Index: 4171789 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.6921. Min Act: -0.1700
Data Index: 5742650 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.6609. Min Act: -0.1700
Data Index: 2473115 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2859. Min Range: -8.2859
Max Act: 7.6921. Min Act: -0.1700
Data Index: 8563617 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19