Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 19 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.3026. Min Act: -0.1700
Data Index: 3524122 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2555. Min Act: -0.1700
Data Index: 4493529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2555. Min Act: -0.1700
Data Index: 3734216 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2555. Min Act: -0.1700
Data Index: 8205883 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 146659 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 4022861 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 4504494 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 532406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 1282463 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2241. Min Act: -0.1700
Data Index: 7365821 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2084. Min Act: -0.1700
Data Index: 80654 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2084. Min Act: -0.1700
Data Index: 8225185 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2084. Min Act: -0.1700
Data Index: 7213029 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.2084. Min Act: -0.1700
Data Index: 8439690 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1927. Min Act: -0.1700
Data Index: 1169079 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1769. Min Act: -0.1700
Data Index: 3532189 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1769. Min Act: -0.1700
Data Index: 4562978 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1769. Min Act: -0.1700
Data Index: 5644049 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1769. Min Act: -0.1700
Data Index: 6311346 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3026. Min Range: -3.3026
Max Act: 3.1769. Min Act: -0.1700
Data Index: 6748554 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19