Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1972 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.4577. Min Act: -0.1700
Data Index: 3717842 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.3327. Min Act: -0.1700
Data Index: 3717841 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.2702. Min Act: -0.1700
Data Index: 5290048 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.1764. Min Act: -0.1700
Data Index: 8639303 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.2077. Min Act: -0.1700
Data Index: 3717844 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.1139. Min Act: -0.1700
Data Index: 3183843 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.1139. Min Act: -0.1700
Data Index: 454096 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.0514. Min Act: -0.1700
Data Index: 340980 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4577. Min Range: -6.4577
Max Act: 6.0202. Min Act: -0.1700
Data Index: 5178953 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8952. Min Act: -0.1700
Data Index: 5530840 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.9264. Min Act: -0.1700
Data Index: 1877590 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8639. Min Act: -0.1700
Data Index: 7144583 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8952. Min Act: -0.1700
Data Index: 7976366 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3732103 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8952. Min Act: -0.1700
Data Index: 3099794 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8952. Min Act: -0.1700
Data Index: 2389980 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8952. Min Act: -0.1700
Data Index: 7986858 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8639. Min Act: -0.1700
Data Index: 2690308 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8327. Min Act: -0.1700
Data Index: 2056586 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4577. Min Range: -6.4577
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3717845 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19