Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4744 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.3435. Min Act: -0.1700
Data Index: 7184485 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.2810. Min Act: -0.1700
Data Index: 7228375 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.2810. Min Act: -0.1700
Data Index: 4590056 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.2185. Min Act: -0.1700
Data Index: 4616051 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.2185. Min Act: -0.1700
Data Index: 6663181 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.2185. Min Act: -0.1700
Data Index: 2734087 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.1560. Min Act: -0.1700
Data Index: 7096317 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 4328368 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 2848940 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 5881682 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 3522575 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 6190120 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 6868956 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0935. Min Act: -0.1700
Data Index: 221847 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0310. Min Act: -0.1700
Data Index: 8138665 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3435. Min Range: -8.3435
Max Act: 7.9685. Min Act: -0.1700
Data Index: 6913857 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0310. Min Act: -0.1700
Data Index: 2972724 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0310. Min Act: -0.1700
Data Index: 702410 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0310. Min Act: -0.1700
Data Index: 6306987 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3435. Min Range: -8.3435
Max Act: 8.0310. Min Act: -0.1700
Data Index: 10582 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19