Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1071 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.3953. Min Act: -0.1700
Data Index: 8346708 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2541. Min Act: -0.1700
Data Index: 5613220 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2698. Min Act: -0.1700
Data Index: 6034268 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2698. Min Act: -0.1700
Data Index: 4137382 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2541. Min Act: -0.1700
Data Index: 5100714 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2698. Min Act: -0.1700
Data Index: 3668473 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 7214506 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 7751645 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 1796833 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 3920293 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 8730242 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 862512 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2384. Min Act: -0.1700
Data Index: 21990 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2226. Min Act: -0.1700
Data Index: 987983 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2226. Min Act: -0.1700
Data Index: 6252446 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2226. Min Act: -0.1700
Data Index: 1388960 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2069. Min Act: -0.1700
Data Index: 7505735 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2069. Min Act: -0.1700
Data Index: 5437337 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2069. Min Act: -0.1700
Data Index: 6832338 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3953. Min Range: -3.3953
Max Act: 3.2069. Min Act: -0.1700
Data Index: 2931133 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19