Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5402 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.4278. Min Act: -0.1700
Data Index: 1802829 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.0840. Min Act: -0.1700
Data Index: 4137220 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4278. Min Range: -4.4278
Max Act: 4.0215. Min Act: -0.1700
Data Index: 316780 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9902. Min Act: -0.1700
Data Index: 7426318 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9590. Min Act: -0.1700
Data Index: 2025773 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9902. Min Act: -0.1700
Data Index: 8330717 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9590. Min Act: -0.1700
Data Index: 2229370 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9277. Min Act: -0.1700
Data Index: 3097747 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8964. Min Act: -0.1700
Data Index: 3657597 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.9277. Min Act: -0.1700
Data Index: 7884279 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8652. Min Act: -0.1700
Data Index: 5102494 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8652. Min Act: -0.1700
Data Index: 2419769 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8652. Min Act: -0.1700
Data Index: 2188730 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8652. Min Act: -0.1700
Data Index: 5071385 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8964. Min Act: -0.1700
Data Index: 8579658 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8652. Min Act: -0.1700
Data Index: 2264797 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8339. Min Act: -0.1700
Data Index: 7675025 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8339. Min Act: -0.1700
Data Index: 613335 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8339. Min Act: -0.1700
Data Index: 3973052 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4278. Min Range: -4.4278
Max Act: 3.8339. Min Act: -0.1700
Data Index: 1000006 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19