Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3366 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.7877. Min Act: -0.1700
Data Index: 8473837 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.7877. Min Act: -0.1700
Data Index: 7482476 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.6002. Min Act: -0.1700
Data Index: 7122850 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.5377. Min Act: -0.1700
Data Index: 5902348 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.4127. Min Act: -0.1700
Data Index: 8637734 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.2252. Min Act: -0.1700
Data Index: 4289754 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.2252. Min Act: -0.1700
Data Index: 3792323 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1627. Min Act: -0.1700
Data Index: 6829362 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1627. Min Act: -0.1700
Data Index: 905949 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1627. Min Act: -0.1700
Data Index: 4882001 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1002. Min Act: -0.1700
Data Index: 6098465 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1002. Min Act: -0.1700
Data Index: 3399157 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1002. Min Act: -0.1700
Data Index: 6739721 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.0377. Min Act: -0.1700
Data Index: 4015265 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7877. Min Range: -11.7877
Max Act: 10.9752. Min Act: -0.1700
Data Index: 7660247 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.1002. Min Act: -0.1700
Data Index: 8755097 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7877. Min Range: -11.7877
Max Act: 11.0377. Min Act: -0.1700
Data Index: 1030191 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7877. Min Range: -11.7877
Max Act: 10.9752. Min Act: -0.1700
Data Index: 6096913 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7877. Min Range: -11.7877
Max Act: 10.9752. Min Act: -0.1700
Data Index: 778827 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7877. Min Range: -11.7877
Max Act: 10.9127. Min Act: -0.1700
Data Index: 4768056 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19