Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1325 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1465. Min Act: -0.1700
Data Index: 5610738 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.1308. Min Act: -0.1700
Data Index: 8780428 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0835. Min Act: -0.1700
Data Index: 5915563 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0677. Min Act: -0.1700
Data Index: 7189460 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0361. Min Act: -0.1700
Data Index: 4932837 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1465. Min Range: -3.1465
Max Act: 3.0046. Min Act: -0.1700
Data Index: 1289562 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9888. Min Act: -0.1700
Data Index: 2187725 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9571. Min Act: -0.1700
Data Index: 6980684 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 3311308 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 7944017 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 8131021 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 8291052 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 2204742 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 6442790 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 4041450 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9413. Min Act: -0.1700
Data Index: 2816528 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9254. Min Act: -0.1700
Data Index: 8131018 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.9096. Min Act: -0.1700
Data Index: 724904 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 3748446 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1465. Min Range: -3.1465
Max Act: 2.8937. Min Act: -0.1700
Data Index: 48739 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19