Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1316 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.3052. Min Act: -0.1700
Data Index: 3050556 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.3052. Min Act: -0.1700
Data Index: 7600972 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.2427. Min Act: -0.1700
Data Index: 4003121 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.1802. Min Act: -0.1700
Data Index: 5035198 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.1802. Min Act: -0.1700
Data Index: 4700575 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.0552. Min Act: -0.1700
Data Index: 1982703 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.0552. Min Act: -0.1700
Data Index: 4830824 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3052. Min Range: -9.3052
Max Act: 9.0552. Min Act: -0.1700
Data Index: 3470872 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.9927. Min Act: -0.1700
Data Index: 2800644 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.9927. Min Act: -0.1700
Data Index: 597393 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.9927. Min Act: -0.1700
Data Index: 900284 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.9927. Min Act: -0.1700
Data Index: 5035188 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.9302. Min Act: -0.1700
Data Index: 1368068 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8677. Min Act: -0.1700
Data Index: 5733566 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8677. Min Act: -0.1700
Data Index: 6175316 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8677. Min Act: -0.1700
Data Index: 4114891 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8677. Min Act: -0.1700
Data Index: 868229 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8052. Min Act: -0.1700
Data Index: 4007097 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.8052. Min Act: -0.1700
Data Index: 5264921 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3052. Min Range: -9.3052
Max Act: 8.7427. Min Act: -0.1700
Data Index: 4206154 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19