Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.6694. Min Act: -0.1700
Data Index: 6282844 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.5756. Min Act: -0.1700
Data Index: 5469648 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.5756. Min Act: -0.1700
Data Index: 4035671 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.5444. Min Act: -0.1700
Data Index: 6896918 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.4819. Min Act: -0.1700
Data Index: 2132867 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.4819. Min Act: -0.1700
Data Index: 266899 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.4194. Min Act: -0.1700
Data Index: 3842858 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2944. Min Act: -0.1700
Data Index: 6720852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2319. Min Act: -0.1700
Data Index: 6749550 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.2319. Min Act: -0.1700
Data Index: 7310295 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 6752104 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 5831637 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 4306901 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 5820714 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1694. Min Act: -0.1700
Data Index: 2484329 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 6667473 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 7766294 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 7111462 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1381. Min Act: -0.1700
Data Index: 6421520 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6694. Min Range: -5.6694
Max Act: 5.1069. Min Act: -0.1700
Data Index: 3257122 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19