Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2444 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.2712. Min Act: -0.1700
Data Index: 1017156 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.2087. Min Act: -0.1700
Data Index: 3843524 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1774. Min Act: -0.1700
Data Index: 7597367 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1462. Min Act: -0.1700
Data Index: 1275763 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1462. Min Act: -0.1700
Data Index: 734042 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1462. Min Act: -0.1700
Data Index: 4167562 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1462. Min Act: -0.1700
Data Index: 6339849 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1149. Min Act: -0.1700
Data Index: 3652710 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4812006 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0524. Min Act: -0.1700
Data Index: 8111979 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0524. Min Act: -0.1700
Data Index: 2734432 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0212. Min Act: -0.1700
Data Index: 1218638 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0212. Min Act: -0.1700
Data Index: 4250099 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0212. Min Act: -0.1700
Data Index: 7806330 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0212. Min Act: -0.1700
Data Index: 8277299 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2712. Min Range: -5.2712
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5176998 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2712. Min Range: -5.2712
Max Act: 4.9899. Min Act: -0.1700
Data Index: 873441 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2712. Min Range: -5.2712
Max Act: 4.9899. Min Act: -0.1700
Data Index: 4959898 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2712. Min Range: -5.2712
Max Act: 4.9899. Min Act: -0.1700
Data Index: 6344987 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2712. Min Range: -5.2712
Max Act: 4.9899. Min Act: -0.1700
Data Index: 5110353 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19