Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.5288. Min Act: -0.1681
Data Index: 6549453 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.5288. Min Act: -0.1700
Data Index: 552126 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.5288. Min Act: -0.1694
Data Index: 7506192 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.4836. Min Act: -0.1700
Data Index: 4835869 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.4108. Min Act: -0.1700
Data Index: 4048145 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.4108. Min Act: -0.1700
Data Index: 130337 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.4108. Min Act: -0.1700
Data Index: 6949716 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3688. Min Act: -0.1685
Data Index: 7500982 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3688. Min Act: -0.1660
Data Index: 925857 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3688. Min Act: -0.1700
Data Index: 2918886 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3688. Min Act: -0.1700
Data Index: 3885946 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3688. Min Act: -0.1684
Data Index: 1225769 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3347. Min Act: -0.1693
Data Index: 2705916 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.3347. Min Act: -0.1700
Data Index: 4892579 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2822. Min Act: -0.1699
Data Index: 8808162 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2759. Min Act: -0.1700
Data Index: 7947882 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2695. Min Act: -0.1700
Data Index: 3338539 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2570. Min Act: -0.1674
Data Index: 5565898 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2570. Min Act: -0.1694
Data Index: 7041024 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5288. Min Range: -0.5288
Max Act: 0.2570. Min Act: -0.1699
Data Index: 6185406 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19