Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4438 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2340. Min Act: -0.1700
Data Index: 7156048 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.2027. Min Act: -0.1700
Data Index: 5542325 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1715. Min Act: -0.1700
Data Index: 4688274 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1715. Min Act: -0.1700
Data Index: 4318429 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.1402. Min Act: -0.1700
Data Index: 8775358 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 2122983 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0777. Min Act: -0.1700
Data Index: 5217127 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0464. Min Act: -0.1700
Data Index: 8158158 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0464. Min Act: -0.1700
Data Index: 8394918 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0464. Min Act: -0.1700
Data Index: 6606446 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0152. Min Act: -0.1700
Data Index: 4561617 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9839. Min Act: -0.1700
Data Index: 4923936 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2340. Min Range: -4.2340
Max Act: 4.0152. Min Act: -0.1700
Data Index: 1856486 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9526. Min Act: -0.1700
Data Index: 2007473 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9839. Min Act: -0.1700
Data Index: 6497541 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9839. Min Act: -0.1700
Data Index: 510860 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9839. Min Act: -0.1700
Data Index: 8230899 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9839. Min Act: -0.1700
Data Index: 1625869 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9526. Min Act: -0.1700
Data Index: 3810787 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2340. Min Range: -4.2340
Max Act: 3.9526. Min Act: -0.1700
Data Index: 7556132 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19