Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1397 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.4539. Min Act: -0.1700
Data Index: 2172187 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.3289. Min Act: -0.1700
Data Index: 3713923 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.2039. Min Act: -0.1700
Data Index: 6159246 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.1101. Min Act: -0.1700
Data Index: 4984362 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.0789. Min Act: -0.1700
Data Index: 1510256 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.0476. Min Act: -0.1700
Data Index: 5091734 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.0789. Min Act: -0.1700
Data Index: 3437976 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4539. Min Range: -5.4539
Max Act: 5.0789. Min Act: -0.1700
Data Index: 8699369 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9851. Min Act: -0.1700
Data Index: 1783712 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9851. Min Act: -0.1700
Data Index: 7384837 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9226. Min Act: -0.1700
Data Index: 1278119 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9539. Min Act: -0.1700
Data Index: 6197634 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9539. Min Act: -0.1700
Data Index: 3105234 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.8914. Min Act: -0.1700
Data Index: 6622479 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9226. Min Act: -0.1700
Data Index: 2143050 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.9226. Min Act: -0.1700
Data Index: 6937934 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.8914. Min Act: -0.1700
Data Index: 7001505 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.8914. Min Act: -0.1700
Data Index: 2857541 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.8601. Min Act: -0.1700
Data Index: 669343 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4539. Min Range: -5.4539
Max Act: 4.8601. Min Act: -0.1700
Data Index: 5419258 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19