Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3030 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.5487. Min Act: -0.1700
Data Index: 8686806 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.4237. Min Act: -0.1700
Data Index: 4474100 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.4549. Min Act: -0.1700
Data Index: 6690834 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.4237. Min Act: -0.1700
Data Index: 4643069 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.3612. Min Act: -0.1700
Data Index: 7640298 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.3299. Min Act: -0.1700
Data Index: 6075096 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.3299. Min Act: -0.1700
Data Index: 2213403 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.3299. Min Act: -0.1700
Data Index: 8244779 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2362. Min Act: -0.1700
Data Index: 6441755 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2987. Min Act: -0.1700
Data Index: 5583590 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2987. Min Act: -0.1700
Data Index: 5446363 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2674. Min Act: -0.1700
Data Index: 7645298 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2674. Min Act: -0.1700
Data Index: 4035675 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2049. Min Act: -0.1700
Data Index: 2059018 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.1424. Min Act: -0.1700
Data Index: 2612268 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.1737. Min Act: -0.1700
Data Index: 3198405 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.1737. Min Act: -0.1700
Data Index: 8596694 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.2049. Min Act: -0.1700
Data Index: 5025021 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.1424. Min Act: -0.1700
Data Index: 8132037 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5487. Min Range: -7.5487
Max Act: 7.0799. Min Act: -0.1700
Data Index: 5789108 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19