Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3677 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.8368. Min Act: -0.1700
Data Index: 5432270 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.2431. Min Act: -0.1700
Data Index: 6913808 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.1493. Min Act: -0.1700
Data Index: 6947387 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.1181. Min Act: -0.1700
Data Index: 8044406 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.0556. Min Act: -0.1700
Data Index: 2201511 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8368. Min Range: -6.8368
Max Act: 6.0243. Min Act: -0.1700
Data Index: 80972 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9618. Min Act: -0.1700
Data Index: 1425731 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9618. Min Act: -0.1700
Data Index: 7136432 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9618. Min Act: -0.1700
Data Index: 1305759 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5096782 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9306. Min Act: -0.1700
Data Index: 8267132 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.9306. Min Act: -0.1700
Data Index: 5180663 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8993. Min Act: -0.1700
Data Index: 6552582 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8993. Min Act: -0.1700
Data Index: 344538 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8681. Min Act: -0.1700
Data Index: 6816923 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8681. Min Act: -0.1700
Data Index: 330390 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8681. Min Act: -0.1700
Data Index: 8145576 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8681. Min Act: -0.1700
Data Index: 1348962 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8368. Min Act: -0.1700
Data Index: 7267927 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8368. Min Range: -6.8368
Max Act: 5.8368. Min Act: -0.1700
Data Index: 3077075 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19