Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2685 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.5084. Min Act: -0.1700
Data Index: 6141587 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.4459. Min Act: -0.1700
Data Index: 7548505 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.4146. Min Act: -0.1700
Data Index: 537493 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.4146. Min Act: -0.1700
Data Index: 6459296 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3834. Min Act: -0.1700
Data Index: 4269108 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3521. Min Act: -0.1700
Data Index: 2999395 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3834. Min Act: -0.1700
Data Index: 3094713 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3521. Min Act: -0.1700
Data Index: 3340947 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3521. Min Act: -0.1700
Data Index: 8748851 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.3521. Min Act: -0.1700
Data Index: 8513689 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2896. Min Act: -0.1700
Data Index: 2630895 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2896. Min Act: -0.1700
Data Index: 4673288 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2896. Min Act: -0.1700
Data Index: 1934635 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2896. Min Act: -0.1700
Data Index: 3718612 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2584. Min Act: -0.1700
Data Index: 5978093 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2584. Min Act: -0.1700
Data Index: 8509266 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2271. Min Act: -0.1700
Data Index: 2528482 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2271. Min Act: -0.1700
Data Index: 4269129 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2271. Min Act: -0.1700
Data Index: 6900351 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5084. Min Range: -5.5084
Max Act: 5.2271. Min Act: -0.1700
Data Index: 3094734 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19