Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2958. Min Range: -7.2958
Max Act: 7.2958. Min Act: -0.1700
Data Index: 2066350 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.8271. Min Act: -0.1700
Data Index: 879247 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.7021. Min Act: -0.1700
Data Index: 6845535 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.5771. Min Act: -0.1700
Data Index: 2056010 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.5771. Min Act: -0.1700
Data Index: 3258490 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.4521. Min Act: -0.1700
Data Index: 4319276 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.4208. Min Act: -0.1700
Data Index: 776810 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.3896. Min Act: -0.1700
Data Index: 497065 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.3896. Min Act: -0.1700
Data Index: 714699 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2958. Min Act: -0.1700
Data Index: 5817131 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2958. Min Act: -0.1700
Data Index: 4618664 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2333. Min Act: -0.1700
Data Index: 8124176 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2333. Min Act: -0.1700
Data Index: 7365600 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2021. Min Act: -0.1700
Data Index: 8361361 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.2021. Min Act: -0.1700
Data Index: 2704604 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3229553 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.1708. Min Act: -0.1700
Data Index: 3229554 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.1083. Min Act: -0.1700
Data Index: 7620256 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.0771. Min Act: -0.1700
Data Index: 6492382 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2958. Min Range: -7.2958
Max Act: 6.0771. Min Act: -0.1700
Data Index: 3665011 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19