Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2428. Min Range: -8.2428
Max Act: 8.2428. Min Act: -0.1700
Data Index: 1567418 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2428. Min Range: -8.2428
Max Act: 8.1178. Min Act: -0.1700
Data Index: 6879929 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2428. Min Range: -8.2428
Max Act: 8.1178. Min Act: -0.1700
Data Index: 707086 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2428. Min Range: -8.2428
Max Act: 8.0553. Min Act: -0.1700
Data Index: 2178970 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2428. Min Range: -8.2428
Max Act: 8.0553. Min Act: -0.1700
Data Index: 7692415 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.9928. Min Act: -0.1700
Data Index: 2409208 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.9303. Min Act: -0.1699
Data Index: 8256909 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 7945137 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 8483911 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 8256935 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 702384 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 2932735 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8678. Min Act: -0.1700
Data Index: 1149787 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.7428. Min Act: -0.1700
Data Index: 1695759 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8053. Min Act: -0.1700
Data Index: 1550255 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8053. Min Act: -0.1700
Data Index: 623696 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8053. Min Act: -0.1700
Data Index: 7504824 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.8053. Min Act: -0.1700
Data Index: 6625980 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.7428. Min Act: -0.1700
Data Index: 7057068 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2428. Min Range: -8.2428
Max Act: 7.7428. Min Act: -0.1700
Data Index: 5658892 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19