Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.6270. Min Act: -0.1700
Data Index: 1866411 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.5221. Min Act: -0.1700
Data Index: 1848860 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.3637. Min Act: -0.1663
Data Index: 7780473 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.3285. Min Act: -0.1694
Data Index: 6022359 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.3285. Min Act: -0.1698
Data Index: 3589456 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2755. Min Act: -0.1699
Data Index: 922449 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2403. Min Act: -0.1700
Data Index: 7008480 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2403. Min Act: -0.1699
Data Index: 4586785 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2403. Min Act: -0.1654
Data Index: 8415936 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2403. Min Act: -0.1700
Data Index: 7361696 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2050. Min Act: -0.1700
Data Index: 3317254 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2050. Min Act: -0.1651
Data Index: 4132090 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2050. Min Act: -0.1683
Data Index: 1630738 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2226. Min Act: -0.1556
Data Index: 1403033 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.2050. Min Act: -0.1696
Data Index: 676985 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.1698. Min Act: -0.1625
Data Index: 8786014 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.1522. Min Act: -0.1618
Data Index: 402634 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.1347. Min Act: -0.1700
Data Index: 578467 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.1347. Min Act: -0.1698
Data Index: 7129394 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6270. Min Range: -1.6270
Max Act: 1.1347. Min Act: -0.1700
Data Index: 6046699 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19