Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3718 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0842. Min Range: -5.0842
Max Act: 5.0842. Min Act: -0.1700
Data Index: 4697912 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0842. Min Range: -5.0842
Max Act: 5.0217. Min Act: -0.1700
Data Index: 2487772 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9592. Min Act: -0.1700
Data Index: 2704346 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9592. Min Act: -0.1700
Data Index: 8301192 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9592. Min Act: -0.1700
Data Index: 2877255 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9279. Min Act: -0.1700
Data Index: 8474106 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9279. Min Act: -0.1700
Data Index: 1398856 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.9279. Min Act: -0.1700
Data Index: 1633802 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8967. Min Act: -0.1700
Data Index: 6124020 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8967. Min Act: -0.1700
Data Index: 4651283 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8654. Min Act: -0.1700
Data Index: 392476 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8654. Min Act: -0.1700
Data Index: 1903948 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8029. Min Act: -0.1700
Data Index: 4483423 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8342. Min Act: -0.1700
Data Index: 3346065 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8342. Min Act: -0.1700
Data Index: 7631266 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8342. Min Act: -0.1700
Data Index: 6336611 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8029. Min Act: -0.1700
Data Index: 6081439 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8029. Min Act: -0.1700
Data Index: 6376093 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.7717. Min Act: -0.1700
Data Index: 673107 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0842. Min Range: -5.0842
Max Act: 4.8029. Min Act: -0.1700
Data Index: 1050222 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19