Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1247 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.2913. Min Act: -0.1700
Data Index: 5614250 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.2288. Min Act: -0.1700
Data Index: 2897909 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.2601. Min Act: -0.1700
Data Index: 6973235 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.1663. Min Act: -0.1700
Data Index: 3752355 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.1663. Min Act: -0.1700
Data Index: 4137319 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.1351. Min Act: -0.1700
Data Index: 5634694 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.1351. Min Act: -0.1700
Data Index: 2593224 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.0726. Min Act: -0.1700
Data Index: 6498516 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.0101. Min Act: -0.1700
Data Index: 8613151 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2913. Min Range: -7.2913
Max Act: 7.0413. Min Act: -0.1700
Data Index: 2854380 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9788. Min Act: -0.1700
Data Index: 4208429 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9476. Min Act: -0.1700
Data Index: 8365760 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9788. Min Act: -0.1700
Data Index: 959257 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9476. Min Act: -0.1700
Data Index: 6096751 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9163. Min Act: -0.1700
Data Index: 5788834 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.9163. Min Act: -0.1700
Data Index: 4493925 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3034128 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.8538. Min Act: -0.1700
Data Index: 3900342 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.8226. Min Act: -0.1700
Data Index: 6369 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2913. Min Range: -7.2913
Max Act: 6.7913. Min Act: -0.1700
Data Index: 6023000 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19