Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.5268. Min Act: -0.1700
Data Index: 607512 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.4018. Min Act: -0.1700
Data Index: 7470224 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.2768. Min Act: -0.1700
Data Index: 6764641 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.2143. Min Act: -0.1700
Data Index: 6474691 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.1518. Min Act: -0.1700
Data Index: 5759665 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.1518. Min Act: -0.1700
Data Index: 6647876 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.0893. Min Act: -0.1700
Data Index: 6167654 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.0268. Min Act: -0.1700
Data Index: 6853248 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5268. Min Range: -9.5268
Max Act: 9.0268. Min Act: -0.1700
Data Index: 5008662 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.9643. Min Act: -0.1700
Data Index: 3655865 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.9643. Min Act: -0.1700
Data Index: 1492662 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.9018. Min Act: -0.1700
Data Index: 2269441 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.9643. Min Act: -0.1700
Data Index: 3035771 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.8393. Min Act: -0.1700
Data Index: 1025842 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.8393. Min Act: -0.1700
Data Index: 5911904 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.7768. Min Act: -0.1700
Data Index: 8552589 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.7143. Min Act: -0.1700
Data Index: 5504296 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.7143. Min Act: -0.1700
Data Index: 7287725 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.7143. Min Act: -0.1700
Data Index: 4459410 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5268. Min Range: -9.5268
Max Act: 8.6518. Min Act: -0.1700
Data Index: 124035 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19