Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2950 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.9223. Min Act: -0.1700
Data Index: 3506888 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.6098. Min Act: -0.1700
Data Index: 5931295 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.5473. Min Act: -0.1700
Data Index: 8530335 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.4848. Min Act: -0.1700
Data Index: 6841193 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.4848. Min Act: -0.1700
Data Index: 8228049 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.4848. Min Act: -0.1700
Data Index: 1772872 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.4223. Min Act: -0.1700
Data Index: 8228050 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.4223. Min Act: -0.1700
Data Index: 8732131 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2973. Min Act: -0.1700
Data Index: 7652060 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2973. Min Act: -0.1700
Data Index: 7971439 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2348. Min Act: -0.1700
Data Index: 1210393 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2348. Min Act: -0.1700
Data Index: 1270891 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2348. Min Act: -0.1700
Data Index: 4162029 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 4709802 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 3118116 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 718754 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.2348. Min Act: -0.1700
Data Index: 718753 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 8547754 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 3180471 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9223. Min Range: -10.9223
Max Act: 10.1723. Min Act: -0.1700
Data Index: 2757056 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19