Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.8250. Min Act: -0.1700
Data Index: 2775249 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.8250. Min Act: -0.1700
Data Index: 1440944 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.4813. Min Act: -0.1700
Data Index: 3040776 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.4188. Min Act: -0.1700
Data Index: 3772848 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.3563. Min Act: -0.1700
Data Index: 7497641 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.3250. Min Act: -0.1700
Data Index: 2661306 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2938. Min Act: -0.1700
Data Index: 8137280 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2938. Min Act: -0.1700
Data Index: 3487997 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.3250. Min Act: -0.1700
Data Index: 4357819 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.3250. Min Act: -0.1700
Data Index: 6979100 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2938. Min Act: -0.1700
Data Index: 8083347 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.3250. Min Act: -0.1700
Data Index: 4990275 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 6371265 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 8343676 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 1922242 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2938. Min Act: -0.1700
Data Index: 8179563 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 2131798 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2313. Min Act: -0.1700
Data Index: 4131345 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 3910438 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8250. Min Range: -6.8250
Max Act: 6.2625. Min Act: -0.1700
Data Index: 233492 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19