Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3379 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.9906. Min Act: -0.1700
Data Index: 1924267 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.9593. Min Act: -0.1700
Data Index: 1302883 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.8030. Min Act: -0.1700
Data Index: 3097712 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.8030. Min Act: -0.1700
Data Index: 586605 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7717. Min Act: -0.1700
Data Index: 5367611 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7404. Min Act: -0.1700
Data Index: 8566247 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7091. Min Act: -0.1700
Data Index: 1436625 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7717. Min Act: -0.1700
Data Index: 4722655 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7091. Min Act: -0.1700
Data Index: 188635 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7091. Min Act: -0.1700
Data Index: 1312487 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.7091. Min Act: -0.1700
Data Index: 8385623 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8693436 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6465. Min Act: -0.1700
Data Index: 4468401 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6778. Min Act: -0.1700
Data Index: 527563 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6309. Min Act: -0.1700
Data Index: 6359977 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6778. Min Act: -0.1700
Data Index: 8010700 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6778. Min Act: -0.1700
Data Index: 2116803 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6465. Min Act: -0.1700
Data Index: 4161946 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6465. Min Act: -0.1700
Data Index: 4232605 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9906. Min Range: -3.9906
Max Act: 3.6465. Min Act: -0.1700
Data Index: 1911542 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19