Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.6623. Min Act: -0.1700
Data Index: 6896832 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.5998. Min Act: -0.1700
Data Index: 487671 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.5373. Min Act: -0.1700
Data Index: 2068730 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.5061. Min Act: -0.1700
Data Index: 8515862 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4436. Min Act: -0.1700
Data Index: 443646 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4748. Min Act: -0.1700
Data Index: 2897696 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4748. Min Act: -0.1700
Data Index: 2680763 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4748. Min Act: -0.1700
Data Index: 5741123 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4748. Min Act: -0.1700
Data Index: 2043433 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4436. Min Act: -0.1700
Data Index: 6949250 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4436. Min Act: -0.1700
Data Index: 6809073 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4436. Min Act: -0.1700
Data Index: 3986985 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4436. Min Act: -0.1700
Data Index: 349451 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5001709 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 734802 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 5228258 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 194932 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 4668967 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 2174011 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6623. Min Range: -4.6623
Max Act: 4.4123. Min Act: -0.1700
Data Index: 1917630 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19