Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.3985. Min Act: -0.1700
Data Index: 476974 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.3673. Min Act: -0.1700
Data Index: 6809807 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1485. Min Act: -0.1700
Data Index: 1943980 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1798. Min Act: -0.1700
Data Index: 97130 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.1173. Min Act: -0.1700
Data Index: 4490971 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0860. Min Act: -0.1700
Data Index: 7696422 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0860. Min Act: -0.1700
Data Index: 1349600 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0860. Min Act: -0.1700
Data Index: 3670142 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0548. Min Act: -0.1700
Data Index: 6883375 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0235. Min Act: -0.1700
Data Index: 5688907 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0235. Min Act: -0.1700
Data Index: 494787 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0235. Min Act: -0.1700
Data Index: 3267460 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3985. Min Range: -6.3985
Max Act: 6.0235. Min Act: -0.1700
Data Index: 1923149 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9298. Min Act: -0.1700
Data Index: 4092696 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.9298. Min Act: -0.1700
Data Index: 7763785 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8985. Min Act: -0.1700
Data Index: 4052321 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8985. Min Act: -0.1700
Data Index: 3523320 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8360. Min Act: -0.1700
Data Index: 5397797 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8985. Min Act: -0.1700
Data Index: 6450328 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3985. Min Range: -6.3985
Max Act: 5.8673. Min Act: -0.1700
Data Index: 4018318 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19