Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6338 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1198. Min Range: -5.1198
Max Act: 5.1198. Min Act: -0.1700
Data Index: 6724855 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.8698. Min Act: -0.1700
Data Index: 5223091 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.7135. Min Act: -0.1700
Data Index: 1345918 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.7135. Min Act: -0.1700
Data Index: 4643655 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.6510. Min Act: -0.1700
Data Index: 2015437 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.6510. Min Act: -0.1700
Data Index: 6890995 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 2677964 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.6510. Min Act: -0.1700
Data Index: 2479494 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.6198. Min Act: -0.1700
Data Index: 2765187 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 2604694 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 6053372 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 542050 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 5656358 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 434377 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5260. Min Act: -0.1700
Data Index: 5743223 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5885. Min Act: -0.1700
Data Index: 1561935 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5573. Min Act: -0.1700
Data Index: 1638697 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5573. Min Act: -0.1700
Data Index: 3004686 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.5260. Min Act: -0.1700
Data Index: 1107945 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1198. Min Range: -5.1198
Max Act: 4.4948. Min Act: -0.1700
Data Index: 3454242 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19