Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 746 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.3065. Min Act: -0.1700
Data Index: 6748474 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.3065. Min Act: -0.1700
Data Index: 3070547 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.3065. Min Act: -0.1700
Data Index: 6487281 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2594. Min Act: -0.1700
Data Index: 3611633 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2436. Min Act: -0.1700
Data Index: 3931953 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2436. Min Act: -0.1700
Data Index: 5782011 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2436. Min Act: -0.1700
Data Index: 3787825 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2279. Min Act: -0.1700
Data Index: 6112630 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2279. Min Act: -0.1700
Data Index: 8334041 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2122. Min Act: -0.1700
Data Index: 5245537 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.2122. Min Act: -0.1700
Data Index: 6548022 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1965. Min Act: -0.1700
Data Index: 7043269 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1965. Min Act: -0.1700
Data Index: 7634641 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1808. Min Act: -0.1700
Data Index: 3602116 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1808. Min Act: -0.1700
Data Index: 8753328 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1808. Min Act: -0.1700
Data Index: 5776481 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1808. Min Act: -0.1700
Data Index: 4033992 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1650. Min Act: -0.1700
Data Index: 1442274 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1493. Min Act: -0.1700
Data Index: 2178731 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3065. Min Range: -3.3065
Max Act: 3.1493. Min Act: -0.1700
Data Index: 5085266 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19