Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 631 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.3336. Min Act: -0.1686
Data Index: 4980980 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.3202. Min Act: -0.1700
Data Index: 7593041 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.3202. Min Act: -0.1699
Data Index: 6848101 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2940. Min Act: -0.1700
Data Index: 5575641 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2748. Min Act: -0.1700
Data Index: 238240 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2876. Min Act: -0.1668
Data Index: 2300281 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2685. Min Act: -0.1700
Data Index: 3000586 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2685. Min Act: -0.1665
Data Index: 219712 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2497. Min Act: -0.1692
Data Index: 3485571 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2435. Min Act: -0.1698
Data Index: 8363847 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2374. Min Act: -0.1700
Data Index: 4456698 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2435. Min Act: -0.1696
Data Index: 776679 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2313. Min Act: -0.1699
Data Index: 4044887 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2435. Min Act: -0.1698
Data Index: 6895930 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2374. Min Act: -0.1698
Data Index: 2561022 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2253. Min Act: -0.1699
Data Index: 4585824 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2313. Min Act: -0.1700
Data Index: 5679059 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2313. Min Act: -0.1680
Data Index: 6915693 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2313. Min Act: -0.1700
Data Index: 1620569 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3336. Min Range: -0.3336
Max Act: 0.2374. Min Act: -0.1698
Data Index: 142070 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19