Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3061 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.5296. Min Act: -0.1700
Data Index: 3528925 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.3421. Min Act: -0.1700
Data Index: 4435595 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.3108. Min Act: -0.1700
Data Index: 3730521 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.2171. Min Act: -0.1700
Data Index: 1881126 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.1233. Min Act: -0.1700
Data Index: 1162501 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.1233. Min Act: -0.1700
Data Index: 4995293 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.1233. Min Act: -0.1700
Data Index: 1881118 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.1546. Min Act: -0.1700
Data Index: 1881129 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0921. Min Act: -0.1700
Data Index: 27544 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0608. Min Act: -0.1700
Data Index: 2188057 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0921. Min Act: -0.1700
Data Index: 1881121 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0608. Min Act: -0.1700
Data Index: 1059777 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0608. Min Act: -0.1700
Data Index: 1828686 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0608. Min Act: -0.1700
Data Index: 7972551 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5296. Min Range: -5.5296
Max Act: 4.9983. Min Act: -0.1700
Data Index: 1451422 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0296. Min Act: -0.1700
Data Index: 1162503 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0296. Min Act: -0.1700
Data Index: 2650765 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5296. Min Range: -5.5296
Max Act: 4.9983. Min Act: -0.1700
Data Index: 148672 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5296. Min Range: -5.5296
Max Act: 4.9983. Min Act: -0.1700
Data Index: 6814991 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5296. Min Range: -5.5296
Max Act: 5.0296. Min Act: -0.1700
Data Index: 7803530 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19