Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3414 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.9502. Min Act: -0.1700
Data Index: 5579150 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.9502. Min Act: -0.1700
Data Index: 2824374 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.8252. Min Act: -0.1700
Data Index: 6292263 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3394585 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3004590 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.7002. Min Act: -0.1700
Data Index: 7792783 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.7315. Min Act: -0.1700
Data Index: 1969927 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6690. Min Act: -0.1700
Data Index: 3865620 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6690. Min Act: -0.1700
Data Index: 4880376 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6377. Min Act: -0.1700
Data Index: 1064378 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6377. Min Act: -0.1700
Data Index: 8083185 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6065. Min Act: -0.1700
Data Index: 571294 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.6065. Min Act: -0.1700
Data Index: 7754869 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5752. Min Act: -0.1700
Data Index: 1699437 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5440. Min Act: -0.1700
Data Index: 78049 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5440. Min Act: -0.1700
Data Index: 2076930 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5440. Min Act: -0.1700
Data Index: 8207760 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5440. Min Act: -0.1700
Data Index: 820119 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5440. Min Act: -0.1700
Data Index: 3324935 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9502. Min Range: -6.9502
Max Act: 6.5127. Min Act: -0.1700
Data Index: 7933844 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19