Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.4220. Min Act: -0.1700
Data Index: 678166 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2970. Min Act: -0.1700
Data Index: 8611783 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2970. Min Act: -0.1700
Data Index: 8484462 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2658. Min Act: -0.1700
Data Index: 2653280 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2345. Min Act: -0.1700
Data Index: 1704099 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2345. Min Act: -0.1700
Data Index: 7823684 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2345. Min Act: -0.1700
Data Index: 1704100 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.2033. Min Act: -0.1700
Data Index: 644979 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6604565 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1720. Min Act: -0.1700
Data Index: 3563783 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1408. Min Act: -0.1700
Data Index: 723444 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1095. Min Act: -0.1700
Data Index: 678169 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1095. Min Act: -0.1700
Data Index: 1999813 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1095. Min Act: -0.1700
Data Index: 2312370 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.1095. Min Act: -0.1700
Data Index: 2049519 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.0470. Min Act: -0.1700
Data Index: 3129738 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.0783. Min Act: -0.1700
Data Index: 2519798 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.0470. Min Act: -0.1700
Data Index: 1439590 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.0158. Min Act: -0.1700
Data Index: 1751596 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4220. Min Range: -5.4220
Max Act: 5.0470. Min Act: -0.1700
Data Index: 7682001 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19