Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3553 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1403. Min Range: -9.1403
Max Act: 9.1403. Min Act: -0.1700
Data Index: 5674458 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.9528. Min Act: -0.1700
Data Index: 8386165 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.9528. Min Act: -0.1700
Data Index: 3551739 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.7653. Min Act: -0.1700
Data Index: 1949368 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.8278. Min Act: -0.1700
Data Index: 588242 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.7653. Min Act: -0.1700
Data Index: 6568032 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.7028. Min Act: -0.1700
Data Index: 3890912 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.6403. Min Act: -0.1700
Data Index: 1157508 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5778. Min Act: -0.1700
Data Index: 2274911 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5778. Min Act: -0.1700
Data Index: 2762612 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5778. Min Act: -0.1700
Data Index: 522572 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 7103419 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 136702 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 336057 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 8490166 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 1654802 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.5153. Min Act: -0.1700
Data Index: 6598893 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.4528. Min Act: -0.1700
Data Index: 6366228 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.4528. Min Act: -0.1700
Data Index: 1393787 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1403. Min Range: -9.1403
Max Act: 8.4528. Min Act: -0.1700
Data Index: 427458 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19