Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.8318. Min Act: -0.1700
Data Index: 6555068 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.8066. Min Act: -0.1700
Data Index: 811901 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.8066. Min Act: -0.1700
Data Index: 8162053 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7648. Min Act: -0.1700
Data Index: 4489274 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7153. Min Act: -0.1700
Data Index: 5518288 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7235. Min Act: -0.1700
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7235. Min Act: -0.1700
Data Index: 4129639 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7153. Min Act: -0.1700
Data Index: 7636281 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.7071. Min Act: -0.1700
Data Index: 7874612 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6908. Min Act: -0.1700
Data Index: 2919568 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6826. Min Act: -0.1700
Data Index: 963642 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6826. Min Act: -0.1700
Data Index: 3246928 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6908. Min Act: -0.1700
Data Index: 5832301 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6745. Min Act: -0.1700
Data Index: 8057148 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6745. Min Act: -0.1700
Data Index: 4752454 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6665. Min Act: -0.1700
Data Index: 2919553 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6584. Min Act: -0.1700
Data Index: 3128750 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6504. Min Act: -0.1700
Data Index: 5764127 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6584. Min Act: -0.1700
Data Index: 5928114 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8318. Min Range: -0.8318
Max Act: 0.6584. Min Act: -0.1700
Data Index: 2970208 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19