Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3894 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.5710. Min Act: -0.1700
Data Index: 6309224 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.3210. Min Act: -0.1700
Data Index: 2743127 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.3210. Min Act: -0.1700
Data Index: 5988443 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1960. Min Act: -0.1700
Data Index: 5427853 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1647. Min Act: -0.1700
Data Index: 5386742 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1960. Min Act: -0.1700
Data Index: 2701458 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1647. Min Act: -0.1700
Data Index: 4488195 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1335. Min Act: -0.1700
Data Index: 652584 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1022. Min Act: -0.1700
Data Index: 3891883 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1335. Min Act: -0.1700
Data Index: 5297103 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1335. Min Act: -0.1700
Data Index: 8155114 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1335. Min Act: -0.1700
Data Index: 5393418 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1022. Min Act: -0.1700
Data Index: 6630225 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0397. Min Act: -0.1700
Data Index: 7787046 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0710. Min Act: -0.1700
Data Index: 8100521 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0710. Min Act: -0.1700
Data Index: 2733579 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0710. Min Act: -0.1700
Data Index: 5460170 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.1022. Min Act: -0.1700
Data Index: 3432146 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0397. Min Act: -0.1700
Data Index: 4457668 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5710. Min Range: -5.5710
Max Act: 5.0397. Min Act: -0.1700
Data Index: 5108155 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19