Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.4833. Min Act: -0.1700
Data Index: 5306912 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.4833. Min Act: -0.1700
Data Index: 4534320 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.3895. Min Act: -0.1700
Data Index: 1438713 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.3270. Min Act: -0.1700
Data Index: 6797710 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2958. Min Act: -0.1700
Data Index: 1462440 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2645. Min Act: -0.1700
Data Index: 6206318 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2645. Min Act: -0.1700
Data Index: 5298700 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2645. Min Act: -0.1700
Data Index: 4894116 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2645. Min Act: -0.1700
Data Index: 6170975 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2333. Min Act: -0.1700
Data Index: 1748171 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2333. Min Act: -0.1700
Data Index: 1880165 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2333. Min Act: -0.1700
Data Index: 2010145 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2333. Min Act: -0.1700
Data Index: 1267122 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2020. Min Act: -0.1700
Data Index: 866346 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4821890 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.1708. Min Act: -0.1700
Data Index: 1771516 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4088019 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.1708. Min Act: -0.1700
Data Index: 4805676 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.1708. Min Act: -0.1700
Data Index: 2994834 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4833. Min Range: -6.4833
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4088016 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19