Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.5553. Min Act: -0.1700
Data Index: 6725026 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.5553. Min Act: -0.1700
Data Index: 8386674 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.4616. Min Act: -0.1700
Data Index: 8423426 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.3991. Min Act: -0.1700
Data Index: 4636704 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.3678. Min Act: -0.1700
Data Index: 7728276 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.3053. Min Act: -0.1700
Data Index: 7141368 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.2741. Min Act: -0.1700
Data Index: 4242838 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.2741. Min Act: -0.1700
Data Index: 280366 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.2116. Min Act: -0.1700
Data Index: 176054 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.2116. Min Act: -0.1700
Data Index: 7379620 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.2116. Min Act: -0.1700
Data Index: 6732661 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 6349710 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 828931 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 6372937 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 3651760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 6841236 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1178. Min Act: -0.1700
Data Index: 6948130 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 7387078 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1491. Min Act: -0.1700
Data Index: 652410 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5553. Min Range: -7.5553
Max Act: 7.1178. Min Act: -0.1700
Data Index: 1298179 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19