Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 671 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0679. Min Range: -6.0679
Max Act: 6.0679. Min Act: -0.1700
Data Index: 767232 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.9116. Min Act: -0.1700
Data Index: 3538241 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8491. Min Act: -0.1700
Data Index: 1687484 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8804. Min Act: -0.1700
Data Index: 7709270 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8491. Min Act: -0.1700
Data Index: 4509131 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8491. Min Act: -0.1700
Data Index: 1489062 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8491. Min Act: -0.1700
Data Index: 892064 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8491. Min Act: -0.1700
Data Index: 6837922 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6511222 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.8179. Min Act: -0.1700
Data Index: 6796267 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7866. Min Act: -0.1700
Data Index: 2791920 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7866. Min Act: -0.1700
Data Index: 1449479 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7866. Min Act: -0.1700
Data Index: 4479821 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7554. Min Act: -0.1700
Data Index: 578052 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7554. Min Act: -0.1700
Data Index: 7608730 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7554. Min Act: -0.1700
Data Index: 6218343 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7241. Min Act: -0.1700
Data Index: 4354477 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7241. Min Act: -0.1700
Data Index: 896214 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7241. Min Act: -0.1700
Data Index: 3859163 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0679. Min Range: -6.0679
Max Act: 5.7241. Min Act: -0.1700
Data Index: 1634175 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19