Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3929 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1462. Min Range: -8.1462
Max Act: 8.1462. Min Act: -0.1700
Data Index: 34003 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 2412250 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 7198117 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.8962. Min Act: -0.1700
Data Index: 3544722 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.7712. Min Act: -0.1700
Data Index: 2660571 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.7087. Min Act: -0.1700
Data Index: 5063723 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.7087. Min Act: -0.1700
Data Index: 6432148 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.6150. Min Act: -0.1700
Data Index: 1534668 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.4587. Min Act: -0.1700
Data Index: 7627979 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.4587. Min Act: -0.1700
Data Index: 8390731 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.4900. Min Act: -0.1700
Data Index: 361969 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.4587. Min Act: -0.1700
Data Index: 2695062 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3962. Min Act: -0.1700
Data Index: 1955616 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3650. Min Act: -0.1700
Data Index: 5904002 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3650. Min Act: -0.1700
Data Index: 8332797 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3025. Min Act: -0.1700
Data Index: 6809230 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3650. Min Act: -0.1700
Data Index: 5946605 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3337. Min Act: -0.1700
Data Index: 8357443 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3025. Min Act: -0.1700
Data Index: 5625292 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1462. Min Range: -8.1462
Max Act: 7.3025. Min Act: -0.1700
Data Index: 3182785 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19