Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2114 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.4924. Min Act: -0.1700
Data Index: 887432 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.3986. Min Act: -0.1700
Data Index: 3807967 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.3049. Min Act: -0.1700
Data Index: 921092 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.2424. Min Act: -0.1700
Data Index: 788771 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.2424. Min Act: -0.1700
Data Index: 4963516 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.1174. Min Act: -0.1700
Data Index: 2360251 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.1174. Min Act: -0.1700
Data Index: 2836652 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.0549. Min Act: -0.1700
Data Index: 6048136 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.0236. Min Act: -0.1700
Data Index: 4360531 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4924. Min Range: -7.4924
Max Act: 7.0236. Min Act: -0.1700
Data Index: 2670260 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.9924. Min Act: -0.1700
Data Index: 6058732 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.9299. Min Act: -0.1700
Data Index: 4192646 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.9611. Min Act: -0.1700
Data Index: 6235548 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.9611. Min Act: -0.1700
Data Index: 5929301 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8674. Min Act: -0.1700
Data Index: 4631513 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8361. Min Act: -0.1700
Data Index: 7647288 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8361. Min Act: -0.1700
Data Index: 8276749 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8361. Min Act: -0.1700
Data Index: 7475029 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8361. Min Act: -0.1700
Data Index: 5222662 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4924. Min Range: -7.4924
Max Act: 6.8361. Min Act: -0.1700
Data Index: 1878843 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19