Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.8311. Min Act: -0.1700
Data Index: 8006118 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.8311. Min Act: -0.1700
Data Index: 5154677 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.8311. Min Act: -0.1700
Data Index: 2995392 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.7061. Min Act: -0.1700
Data Index: 1635762 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6749. Min Act: -0.1700
Data Index: 4975407 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6749. Min Act: -0.1700
Data Index: 2939833 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6749. Min Act: -0.1700
Data Index: 5422624 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.7061. Min Act: -0.1700
Data Index: 283477 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6749. Min Act: -0.1700
Data Index: 7307938 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6124. Min Act: -0.1700
Data Index: 181058 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6436. Min Act: -0.1700
Data Index: 5629318 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6124. Min Act: -0.1700
Data Index: 6436188 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 6339773 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 7592193 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.6124. Min Act: -0.1700
Data Index: 8772783 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5499. Min Act: -0.1700
Data Index: 4577600 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 4198445 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 671953 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 2715425 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8311. Min Range: -4.8311
Max Act: 4.5811. Min Act: -0.1700
Data Index: 4118354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19