Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3674 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.4703. Min Act: -0.1700
Data Index: 5503856 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.3453. Min Act: -0.1700
Data Index: 1760284 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.3453. Min Act: -0.1700
Data Index: 1914793 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.3140. Min Act: -0.1700
Data Index: 6200896 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2828. Min Act: -0.1700
Data Index: 3647334 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2515. Min Act: -0.1700
Data Index: 542828 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2515. Min Act: -0.1700
Data Index: 559322 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2515. Min Act: -0.1700
Data Index: 2879262 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2203. Min Act: -0.1700
Data Index: 4700825 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2203. Min Act: -0.1700
Data Index: 5159850 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.1890. Min Act: -0.1700
Data Index: 88723 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.2203. Min Act: -0.1700
Data Index: 455380 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.1578. Min Act: -0.1700
Data Index: 7804909 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.1265. Min Act: -0.1700
Data Index: 2235822 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.0953. Min Act: -0.1700
Data Index: 5593239 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.1265. Min Act: -0.1700
Data Index: 2235813 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.1265. Min Act: -0.1700
Data Index: 542830 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.0953. Min Act: -0.1700
Data Index: 1673050 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.0640. Min Act: -0.1700
Data Index: 2235816 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4703. Min Range: -7.4703
Max Act: 7.0640. Min Act: -0.1700
Data Index: 3903925 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19