Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2789 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.4845. Min Act: -0.1700
Data Index: 4588783 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.2970. Min Act: -0.1700
Data Index: 15113 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.1720. Min Act: -0.1700
Data Index: 3549328 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.0783. Min Act: -0.1700
Data Index: 1265543 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.0783. Min Act: -0.1700
Data Index: 3045406 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4845. Min Range: -6.4845
Max Act: 6.0158. Min Act: -0.1700
Data Index: 7013378 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9845. Min Act: -0.1700
Data Index: 711180 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 5946378 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 8018433 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9845. Min Act: -0.1700
Data Index: 4625712 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7533516 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7801279 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7995112 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 3113217 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9533. Min Act: -0.1700
Data Index: 33188 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9220. Min Act: -0.1700
Data Index: 3596766 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9220. Min Act: -0.1700
Data Index: 5927630 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.9220. Min Act: -0.1700
Data Index: 3713379 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.8595. Min Act: -0.1700
Data Index: 5422014 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4845. Min Range: -6.4845
Max Act: 5.8595. Min Act: -0.1700
Data Index: 1682156 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19