Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2541 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0188. Min Range: -7.0188
Max Act: 7.0188. Min Act: -0.1700
Data Index: 2859412 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.8625. Min Act: -0.1700
Data Index: 5901418 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.8000. Min Act: -0.1700
Data Index: 2271056 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.6750. Min Act: -0.1700
Data Index: 6210190 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.5813. Min Act: -0.1700
Data Index: 4636700 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.5188. Min Act: -0.1700
Data Index: 8752326 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.5813. Min Act: -0.1700
Data Index: 6323003 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.5188. Min Act: -0.1700
Data Index: 7857726 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4563. Min Act: -0.1700
Data Index: 3501579 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4563. Min Act: -0.1700
Data Index: 1466429 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4563. Min Act: -0.1700
Data Index: 2627241 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4875. Min Act: -0.1700
Data Index: 273954 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4563. Min Act: -0.1700
Data Index: 7221457 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4250. Min Act: -0.1700
Data Index: 8715356 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.3938. Min Act: -0.1700
Data Index: 768459 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.3938. Min Act: -0.1700
Data Index: 2626605 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.4250. Min Act: -0.1700
Data Index: 8514396 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.3938. Min Act: -0.1700
Data Index: 3752820 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.3938. Min Act: -0.1700
Data Index: 4225080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0188. Min Range: -7.0188
Max Act: 6.3938. Min Act: -0.1700
Data Index: 5845723 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19