Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3670 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.6484. Min Act: -0.1700
Data Index: 7725419 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.5234. Min Act: -0.1700
Data Index: 8698453 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.4609. Min Act: -0.1700
Data Index: 4000183 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.3359. Min Act: -0.1700
Data Index: 2061101 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.3984. Min Act: -0.1700
Data Index: 8458841 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.3359. Min Act: -0.1700
Data Index: 2705667 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.3359. Min Act: -0.1700
Data Index: 4103903 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.3047. Min Act: -0.1700
Data Index: 927441 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2734. Min Act: -0.1700
Data Index: 8554682 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2422. Min Act: -0.1700
Data Index: 2680617 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2422. Min Act: -0.1700
Data Index: 653912 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2734. Min Act: -0.1700
Data Index: 2575834 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2109. Min Act: -0.1700
Data Index: 6561628 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.2109. Min Act: -0.1700
Data Index: 2061108 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1797. Min Act: -0.1700
Data Index: 8268532 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1797. Min Act: -0.1700
Data Index: 810681 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1172. Min Act: -0.1700
Data Index: 1012358 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1172. Min Act: -0.1700
Data Index: 4511783 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1484. Min Act: -0.1700
Data Index: 1445876 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6484. Min Range: -8.6484
Max Act: 8.1172. Min Act: -0.1700
Data Index: 6552158 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19