Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4709 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.7316. Min Act: -0.1700
Data Index: 1514123 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5751. Min Act: -0.1700
Data Index: 3698515 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5751. Min Act: -0.1700
Data Index: 4004490 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5125. Min Act: -0.1700
Data Index: 7469648 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5438. Min Act: -0.1700
Data Index: 2395277 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5125. Min Act: -0.1700
Data Index: 7885268 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4812. Min Act: -0.1700
Data Index: 5158704 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5125. Min Act: -0.1700
Data Index: 5565329 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4498. Min Act: -0.1700
Data Index: 5221271 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.5125. Min Act: -0.1700
Data Index: 1074147 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 8586471 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4498. Min Act: -0.1700
Data Index: 3949831 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4812. Min Act: -0.1700
Data Index: 8730273 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4498. Min Act: -0.1700
Data Index: 5432300 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 4478767 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 8360096 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 7611151 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 8492908 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.4185. Min Act: -0.1700
Data Index: 6677979 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7316. Min Range: -3.7316
Max Act: 3.3714. Min Act: -0.1700
Data Index: 8350856 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19