Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.9426. Min Act: -0.1700
Data Index: 8397562 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.8801. Min Act: -0.1700
Data Index: 5977868 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.8176. Min Act: -0.1700
Data Index: 953929 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.7864. Min Act: -0.1700
Data Index: 3337542 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.7864. Min Act: -0.1700
Data Index: 7529431 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.7239. Min Act: -0.1700
Data Index: 7265270 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6926. Min Act: -0.1700
Data Index: 517211 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6614. Min Act: -0.1700
Data Index: 8486229 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6614. Min Act: -0.1700
Data Index: 6236851 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1025151 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6301. Min Act: -0.1700
Data Index: 894465 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.6301. Min Act: -0.1700
Data Index: 6701905 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5989. Min Act: -0.1700
Data Index: 2464452 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5989. Min Act: -0.1700
Data Index: 8031181 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5989. Min Act: -0.1700
Data Index: 5670200 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5989. Min Act: -0.1700
Data Index: 16981 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5676. Min Act: -0.1700
Data Index: 8614608 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5676. Min Act: -0.1700
Data Index: 3777547 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5989. Min Act: -0.1700
Data Index: 517210 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9426. Min Range: -5.9426
Max Act: 5.5676. Min Act: -0.1700
Data Index: 4920434 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19