Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.4693. Min Act: -0.1700
Data Index: 6754140 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.5318. Min Act: -0.1700
Data Index: 6754156 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.2818. Min Act: -0.1700
Data Index: 7479814 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.2193. Min Act: -0.1700
Data Index: 5538591 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.1568. Min Act: -0.1700
Data Index: 4381168 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5318. Min Range: -10.5318
Max Act: 10.0943. Min Act: -0.1700
Data Index: 6107946 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.9693. Min Act: -0.1700
Data Index: 4890941 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 7285883 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 1347039 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 3604106 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 7538760 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 7532366 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 893457 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.7818. Min Act: -0.1700
Data Index: 5474265 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.8443. Min Act: -0.1700
Data Index: 3703566 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.7193. Min Act: -0.1700
Data Index: 481942 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.7193. Min Act: -0.1700
Data Index: 2111029 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.6568. Min Act: -0.1700
Data Index: 4355813 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.7193. Min Act: -0.1700
Data Index: 7095658 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5318. Min Range: -10.5318
Max Act: 9.7193. Min Act: -0.1700
Data Index: 6140409 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19