Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4759. Min Range: -9.4759
Max Act: 9.4759. Min Act: -0.1700
Data Index: 4540216 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4759. Min Range: -9.4759
Max Act: 8.2259. Min Act: -0.1700
Data Index: 3509866 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.8509. Min Act: -0.1700
Data Index: 7340226 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.6322. Min Act: -0.1700
Data Index: 5282982 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.5384. Min Act: -0.1700
Data Index: 7145779 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.5697. Min Act: -0.1700
Data Index: 3344628 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.5072. Min Act: -0.1700
Data Index: 4083420 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.3822. Min Act: -0.1700
Data Index: 5086389 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.4134. Min Act: -0.1700
Data Index: 2644642 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.3822. Min Act: -0.1700
Data Index: 8006807 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.3509. Min Act: -0.1700
Data Index: 6024771 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.3197. Min Act: -0.1700
Data Index: 2654419 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.3197. Min Act: -0.1700
Data Index: 5918154 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2884. Min Act: -0.1700
Data Index: 787378 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2884. Min Act: -0.1700
Data Index: 787247 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2259. Min Act: -0.1700
Data Index: 4606952 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2572. Min Act: -0.1700
Data Index: 1885630 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2572. Min Act: -0.1700
Data Index: 5897955 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2259. Min Act: -0.1700
Data Index: 3024731 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4759. Min Range: -9.4759
Max Act: 7.2259. Min Act: -0.1700
Data Index: 2050940 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19