Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.6557. Min Act: -0.1700
Data Index: 6742735 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.5305. Min Act: -0.1700
Data Index: 7616160 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.5462. Min Act: -0.1700
Data Index: 1866028 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.4835. Min Act: -0.1700
Data Index: 873828 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.4522. Min Act: -0.1700
Data Index: 2921330 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.4052. Min Act: -0.1700
Data Index: 2921334 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.3581. Min Act: -0.1700
Data Index: 2386898 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.3425. Min Act: -0.1700
Data Index: 1302164 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.3111. Min Act: -0.1700
Data Index: 7388236 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.3111. Min Act: -0.1700
Data Index: 4342437 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2954. Min Act: -0.1700
Data Index: 7631788 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2797. Min Act: -0.1700
Data Index: 3156553 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2483. Min Act: -0.1700
Data Index: 6973669 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2640. Min Act: -0.1700
Data Index: 8082321 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2483. Min Act: -0.1700
Data Index: 1988087 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2325. Min Act: -0.1700
Data Index: 2118961 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2325. Min Act: -0.1700
Data Index: 5244903 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2325. Min Act: -0.1700
Data Index: 7138897 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2325. Min Act: -0.1700
Data Index: 2814455 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6557. Min Range: -3.6557
Max Act: 3.2325. Min Act: -0.1700
Data Index: 8283071 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19