Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4804 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.7895. Min Act: -0.1700
Data Index: 2188329 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.7583. Min Act: -0.1700
Data Index: 3674135 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.4770. Min Act: -0.1700
Data Index: 370177 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.4145. Min Act: -0.1700
Data Index: 1793827 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.4145. Min Act: -0.1700
Data Index: 2188328 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.3520. Min Act: -0.1700
Data Index: 635017 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2895. Min Act: -0.1700
Data Index: 3119607 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2895. Min Act: -0.1700
Data Index: 2188327 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2583. Min Act: -0.1700
Data Index: 2003298 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2583. Min Act: -0.1700
Data Index: 4578873 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2270. Min Act: -0.1700
Data Index: 1087382 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.2270. Min Act: -0.1700
Data Index: 8503225 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.1958. Min Act: -0.1700
Data Index: 3229931 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.1958. Min Act: -0.1700
Data Index: 7887502 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.1645. Min Act: -0.1700
Data Index: 5532791 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.1645. Min Act: -0.1700
Data Index: 346570 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.0708. Min Act: -0.1700
Data Index: 4337605 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.0708. Min Act: -0.1700
Data Index: 1444250 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.0708. Min Act: -0.1700
Data Index: 2756655 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7895. Min Range: -7.7895
Max Act: 7.0395. Min Act: -0.1700
Data Index: 7908892 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19