Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5973 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.2337. Min Act: -0.1700
Data Index: 7381252 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1708. Min Act: -0.1700
Data Index: 31526 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1551. Min Act: -0.1700
Data Index: 2795987 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1551. Min Act: -0.1700
Data Index: 1798525 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1551. Min Act: -0.1700
Data Index: 4049756 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1551. Min Act: -0.1700
Data Index: 5240154 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1393. Min Act: -0.1700
Data Index: 8753790 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1393. Min Act: -0.1700
Data Index: 1680771 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1393. Min Act: -0.1700
Data Index: 973702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1393. Min Act: -0.1700
Data Index: 8370027 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1393. Min Act: -0.1700
Data Index: 1458368 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 4885664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 7184717 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 7096644 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 3937381 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 185379 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 3046762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1236. Min Act: -0.1700
Data Index: 6079552 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1078. Min Act: -0.1700
Data Index: 1610143 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2337. Min Range: -3.2337
Max Act: 3.1078. Min Act: -0.1700
Data Index: 2756524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19