Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4607 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6975. Min Act: -0.1700
Data Index: 4095095 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6975. Min Act: -0.1700
Data Index: 7388178 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6662. Min Act: -0.1700
Data Index: 6920675 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6662. Min Act: -0.1700
Data Index: 3837274 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6662. Min Act: -0.1700
Data Index: 361630 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6350. Min Act: -0.1700
Data Index: 577253 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6037. Min Act: -0.1700
Data Index: 7778948 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.6037. Min Act: -0.1700
Data Index: 1580277 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 6001743 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5412. Min Act: -0.1700
Data Index: 3353145 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 5193554 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 5950391 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 5706756 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 7074457 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5412. Min Act: -0.1700
Data Index: 5852302 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5725. Min Act: -0.1700
Data Index: 8695925 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5412. Min Act: -0.1700
Data Index: 7108051 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5412. Min Act: -0.1700
Data Index: 4327851 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5100. Min Act: -0.1700
Data Index: 551618 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6975. Min Range: -6.6975
Max Act: 6.5100. Min Act: -0.1700
Data Index: 2334202 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19