Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2154 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6306. Min Range: -5.6306
Max Act: 5.6306. Min Act: -0.1700
Data Index: 2899571 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6306. Min Range: -5.6306
Max Act: 5.3181. Min Act: -0.1700
Data Index: 2931087 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6306. Min Range: -5.6306
Max Act: 5.0368. Min Act: -0.1700
Data Index: 1670795 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6306. Min Range: -5.6306
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3045149 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9743. Min Act: -0.1700
Data Index: 5913692 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6306. Min Range: -5.6306
Max Act: 5.0056. Min Act: -0.1700
Data Index: 6613863 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9431. Min Act: -0.1700
Data Index: 4712905 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9431. Min Act: -0.1700
Data Index: 5155818 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9118. Min Act: -0.1700
Data Index: 6969574 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9431. Min Act: -0.1700
Data Index: 6048255 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.9118. Min Act: -0.1700
Data Index: 1617488 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8806. Min Act: -0.1700
Data Index: 8648241 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8806. Min Act: -0.1700
Data Index: 1617883 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 4031649 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 6066587 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 3107417 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 7766644 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 2579627 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 8024085 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6306. Min Range: -5.6306
Max Act: 4.8493. Min Act: -0.1700
Data Index: 5162747 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19