Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2534 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.8239. Min Act: -0.1700
Data Index: 2616642 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.6364. Min Act: -0.1699
Data Index: 8428755 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.5739. Min Act: -0.1700
Data Index: 2034155 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.4489. Min Act: -0.1699
Data Index: 1503616 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.4489. Min Act: -0.1700
Data Index: 758009 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.3864. Min Act: -0.1699
Data Index: 2924516 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.3864. Min Act: -0.1700
Data Index: 7631185 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.3864. Min Act: -0.1700
Data Index: 3015757 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.3239. Min Act: -0.1700
Data Index: 2405342 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.3864. Min Act: -0.1700
Data Index: 8676732 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 5819894 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 6102838 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 5260711 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 8241750 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.1989. Min Act: -0.1700
Data Index: 6895612 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1695
Data Index: 963683 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 3300370 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1699
Data Index: 8248529 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1699
Data Index: 402452 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8239. Min Range: -9.8239
Max Act: 9.2614. Min Act: -0.1700
Data Index: 4706019 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19