Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4034 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.1493. Min Act: -0.1700
Data Index: 771033 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0824. Min Act: -0.1700
Data Index: 8064919 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0320. Min Act: -0.1700
Data Index: 782248 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0488. Min Act: -0.1700
Data Index: 2654296 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0320. Min Act: -0.1700
Data Index: 4788150 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0151. Min Act: -0.1700
Data Index: 5255130 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0151. Min Act: -0.1700
Data Index: 2233292 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9982. Min Act: -0.1700
Data Index: 1562940 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1493. Min Range: -2.1493
Max Act: 2.0151. Min Act: -0.1700
Data Index: 404309 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 2836689 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 3443550 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 4008685 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 1987927 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 5847663 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9644. Min Act: -0.1700
Data Index: 7700652 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9813. Min Act: -0.1700
Data Index: 7207048 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9644. Min Act: -0.1700
Data Index: 2353046 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9474. Min Act: -0.1700
Data Index: 5762290 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9474. Min Act: -0.1700
Data Index: 4444215 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1493. Min Range: -2.1493
Max Act: 1.9644. Min Act: -0.1700
Data Index: 8015053 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19