Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1505 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.9480. Min Act: -0.1700
Data Index: 2319938 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.6667. Min Act: -0.1700
Data Index: 6585243 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.6042. Min Act: -0.1700
Data Index: 5675189 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.6355. Min Act: -0.1700
Data Index: 5510539 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.5417. Min Act: -0.1700
Data Index: 3297524 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.5417. Min Act: -0.1700
Data Index: 3483252 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.5417. Min Act: -0.1700
Data Index: 6345412 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 3421483 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.5417. Min Act: -0.1700
Data Index: 5751315 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 427014 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 2380402 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 2908639 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 1639240 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 6821478 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4792. Min Act: -0.1700
Data Index: 4062196 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4167. Min Act: -0.1700
Data Index: 6795722 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4167. Min Act: -0.1700
Data Index: 3098034 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.4167. Min Act: -0.1700
Data Index: 4760548 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.3855. Min Act: -0.1700
Data Index: 1488946 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9480. Min Range: -5.9480
Max Act: 5.3855. Min Act: -0.1700
Data Index: 6113021 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19