Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1643. Min Range: -4.1643
Max Act: 4.1643. Min Act: -0.1700
Data Index: 2371711 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8517. Min Act: -0.1700
Data Index: 7362469 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.8361. Min Act: -0.1700
Data Index: 6516339 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.7736. Min Act: -0.1700
Data Index: 167356 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.7266. Min Act: -0.1700
Data Index: 1867299 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.7110. Min Act: -0.1700
Data Index: 465342 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.6953. Min Act: -0.1700
Data Index: 2506727 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.6641. Min Act: -0.1700
Data Index: 1467586 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.6171. Min Act: -0.1700
Data Index: 8432534 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.6171. Min Act: -0.1700
Data Index: 7119135 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5702. Min Act: -0.1700
Data Index: 8720219 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5545. Min Act: -0.1700
Data Index: 1742527 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5545. Min Act: -0.1700
Data Index: 670888 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5388. Min Act: -0.1700
Data Index: 646801 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5388. Min Act: -0.1700
Data Index: 2182761 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5075. Min Act: -0.1700
Data Index: 5114002 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5075. Min Act: -0.1700
Data Index: 6230288 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.4919. Min Act: -0.1700
Data Index: 1854718 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5232. Min Act: -0.1700
Data Index: 4536709 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1643. Min Range: -4.1643
Max Act: 3.5075. Min Act: -0.1700
Data Index: 2014879 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19