Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5374 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.3417. Min Act: -0.1700
Data Index: 2237103 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.2792. Min Act: -0.1700
Data Index: 2504229 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.2479. Min Act: -0.1700
Data Index: 5177192 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.2479. Min Act: -0.1700
Data Index: 6550695 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1854. Min Act: -0.1700
Data Index: 3218059 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1854. Min Act: -0.1700
Data Index: 493175 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1542. Min Act: -0.1700
Data Index: 7980879 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1542. Min Act: -0.1700
Data Index: 7202006 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1542. Min Act: -0.1700
Data Index: 2717993 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1854. Min Act: -0.1700
Data Index: 4887071 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.1229. Min Act: -0.1700
Data Index: 1245908 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0917. Min Act: -0.1700
Data Index: 5527960 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0917. Min Act: -0.1700
Data Index: 8642156 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0917. Min Act: -0.1700
Data Index: 8503021 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0604. Min Act: -0.1700
Data Index: 7452548 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0604. Min Act: -0.1700
Data Index: 4079191 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0604. Min Act: -0.1700
Data Index: 1442575 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0292. Min Act: -0.1700
Data Index: 3411295 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0292. Min Act: -0.1700
Data Index: 6618550 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3417. Min Range: -5.3417
Max Act: 5.0292. Min Act: -0.1700
Data Index: 6104029 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19