Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6380 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2401. Min Range: -8.2401
Max Act: 8.2401. Min Act: -0.1700
Data Index: 7522798 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2401. Min Range: -8.2401
Max Act: 8.2401. Min Act: -0.1700
Data Index: 5618714 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2401. Min Range: -8.2401
Max Act: 8.0526. Min Act: -0.1700
Data Index: 8120755 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.9276. Min Act: -0.1700
Data Index: 7689180 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.9276. Min Act: -0.1700
Data Index: 1361781 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.8026. Min Act: -0.1700
Data Index: 472665 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.8026. Min Act: -0.1700
Data Index: 2422537 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.7401. Min Act: -0.1700
Data Index: 2857254 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.7401. Min Act: -0.1700
Data Index: 549399 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.7401. Min Act: -0.1700
Data Index: 5116085 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.7088. Min Act: -0.1700
Data Index: 6665215 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6151. Min Act: -0.1700
Data Index: 6848507 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6463. Min Act: -0.1700
Data Index: 6325328 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6463. Min Act: -0.1700
Data Index: 5381182 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6151. Min Act: -0.1700
Data Index: 5687986 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6151. Min Act: -0.1700
Data Index: 3019047 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.6463. Min Act: -0.1700
Data Index: 323859 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.5838. Min Act: -0.1700
Data Index: 1484974 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.5838. Min Act: -0.1700
Data Index: 6131281 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2401. Min Range: -8.2401
Max Act: 7.5526. Min Act: -0.1700
Data Index: 5253351 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19