Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1471 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1387. Min Range: -5.1387
Max Act: 5.1387. Min Act: -0.1700
Data Index: 1285127 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.9200. Min Act: -0.1700
Data Index: 8775867 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.9200. Min Act: -0.1700
Data Index: 3820832 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.8887. Min Act: -0.1700
Data Index: 4153795 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.8575. Min Act: -0.1700
Data Index: 4051568 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7950. Min Act: -0.1700
Data Index: 474530 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.8262. Min Act: -0.1700
Data Index: 6930342 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.8262. Min Act: -0.1700
Data Index: 5708884 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7637. Min Act: -0.1700
Data Index: 8183026 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7325. Min Act: -0.1700
Data Index: 3965433 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7325. Min Act: -0.1700
Data Index: 7910009 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7012. Min Act: -0.1700
Data Index: 5580115 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7325. Min Act: -0.1700
Data Index: 4376443 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7012. Min Act: -0.1700
Data Index: 3164136 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7012. Min Act: -0.1700
Data Index: 3143042 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.6700. Min Act: -0.1700
Data Index: 237482 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.7012. Min Act: -0.1700
Data Index: 7018930 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.6075. Min Act: -0.1700
Data Index: 4068480 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.6387. Min Act: -0.1700
Data Index: 7328470 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1387. Min Range: -5.1387
Max Act: 4.6387. Min Act: -0.1700
Data Index: 507217 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19