Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5047 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.9380. Min Act: -0.1700
Data Index: 1646933 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6565. Min Act: -0.1700
Data Index: 2969016 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6565. Min Act: -0.1700
Data Index: 3881129 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6252. Min Act: -0.1700
Data Index: 2378179 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6096. Min Act: -0.1700
Data Index: 3275377 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6252. Min Act: -0.1700
Data Index: 8514816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5939. Min Act: -0.1700
Data Index: 6550619 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.6096. Min Act: -0.1700
Data Index: 6701582 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5939. Min Act: -0.1700
Data Index: 7746687 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5783. Min Act: -0.1700
Data Index: 2145193 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5783. Min Act: -0.1700
Data Index: 5293175 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 766089 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 3158207 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 315947 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 8689622 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 2542741 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 4254386 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 4385408 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5626. Min Act: -0.1700
Data Index: 5406065 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9380. Min Range: -3.9380
Max Act: 3.5470. Min Act: -0.1700
Data Index: 4027388 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #19