Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3536 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.8530. Min Act: -0.1700
Data Index: 4786188 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.7593. Min Act: -0.1700
Data Index: 6988396 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.7593. Min Act: -0.1700
Data Index: 4189462 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.7280. Min Act: -0.1700
Data Index: 2997188 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.7280. Min Act: -0.1700
Data Index: 3218634 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6655. Min Act: -0.1700
Data Index: 7567392 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6343. Min Act: -0.1700
Data Index: 6690005 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6343. Min Act: -0.1700
Data Index: 341614 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6343. Min Act: -0.1700
Data Index: 5864524 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6343. Min Act: -0.1700
Data Index: 3483231 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6343. Min Act: -0.1700
Data Index: 1525144 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1949235 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5718. Min Act: -0.1700
Data Index: 6907560 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 8790042 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5718. Min Act: -0.1700
Data Index: 7856118 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 4786057 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1695194 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 8365472 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 1159820 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5405. Min Act: -0.1700
Data Index: 8687297 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19