Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4994 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.2922. Min Act: -0.1700
Data Index: 5766587 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.2922. Min Act: -0.1700
Data Index: 5510554 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.2609. Min Act: -0.1700
Data Index: 7841123 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.2297. Min Act: -0.1700
Data Index: 6263789 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1984. Min Act: -0.1700
Data Index: 5557443 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1984. Min Act: -0.1700
Data Index: 2211959 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1984. Min Act: -0.1700
Data Index: 4931639 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 3616139 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 2812994 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 6628336 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 1534200 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 1271072 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 5828913 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1672. Min Act: -0.1700
Data Index: 6375143 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1359. Min Act: -0.1700
Data Index: 7266546 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1359. Min Act: -0.1700
Data Index: 110626 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1359. Min Act: -0.1700
Data Index: 3561367 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1359. Min Act: -0.1700
Data Index: 6573330 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1359. Min Act: -0.1700
Data Index: 3376798 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2922. Min Range: -4.2922
Max Act: 4.1047. Min Act: -0.1700
Data Index: 2458156 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19