Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3567 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.4416. Min Act: -0.1700
Data Index: 5831384 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.3166. Min Act: -0.1700
Data Index: 4822083 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.2541. Min Act: -0.1700
Data Index: 7972078 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.2541. Min Act: -0.1700
Data Index: 4264274 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.1916. Min Act: -0.1700
Data Index: 7300910 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.1916. Min Act: -0.1700
Data Index: 5916716 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.0666. Min Act: -0.1700
Data Index: 3541265 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.0666. Min Act: -0.1700
Data Index: 6486284 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.0666. Min Act: -0.1700
Data Index: 2884610 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4416. Min Range: -9.4416
Max Act: 9.0041. Min Act: -0.1700
Data Index: 3095989 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.9416. Min Act: -0.1700
Data Index: 2154591 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.9416. Min Act: -0.1700
Data Index: 2867845 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.9416. Min Act: -0.1700
Data Index: 4472381 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.8791. Min Act: -0.1700
Data Index: 7214044 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.8166. Min Act: -0.1700
Data Index: 3925706 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.8166. Min Act: -0.1700
Data Index: 7079768 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.8166. Min Act: -0.1700
Data Index: 8041435 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.8166. Min Act: -0.1700
Data Index: 127479 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.7541. Min Act: -0.1700
Data Index: 7295651 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4416. Min Range: -9.4416
Max Act: 8.7541. Min Act: -0.1700
Data Index: 1272836 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19