Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3404 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.7467. Min Act: -0.1700
Data Index: 5764146 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.5905. Min Act: -0.1700
Data Index: 8337417 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.4655. Min Act: -0.1700
Data Index: 7401036 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.4342. Min Act: -0.1700
Data Index: 8474539 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.4030. Min Act: -0.1700
Data Index: 5027148 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3717. Min Act: -0.1700
Data Index: 2709084 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3717. Min Act: -0.1700
Data Index: 8078154 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3717. Min Act: -0.1700
Data Index: 3381403 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3405. Min Act: -0.1700
Data Index: 6843994 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3405. Min Act: -0.1700
Data Index: 2510779 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3092. Min Act: -0.1700
Data Index: 5157698 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3092. Min Act: -0.1700
Data Index: 545570 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3092. Min Act: -0.1700
Data Index: 1906617 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3092. Min Act: -0.1700
Data Index: 4779103 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.3092. Min Act: -0.1700
Data Index: 3952882 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.2780. Min Act: -0.1700
Data Index: 7668260 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8508237 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.2780. Min Act: -0.1700
Data Index: 8169672 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.2467. Min Act: -0.1700
Data Index: 7392999 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7467. Min Range: -5.7467
Max Act: 5.2780. Min Act: -0.1700
Data Index: 5486818 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19