Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0184. Min Range: -5.0184
Max Act: 5.0184. Min Act: -0.1700
Data Index: 3046175 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.9559. Min Act: -0.1700
Data Index: 6801519 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.9247. Min Act: -0.1700
Data Index: 6903978 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8622. Min Act: -0.1700
Data Index: 4095646 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8622. Min Act: -0.1700
Data Index: 2265433 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8622. Min Act: -0.1700
Data Index: 1447369 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8622. Min Act: -0.1700
Data Index: 5686839 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8309. Min Act: -0.1700
Data Index: 4459632 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8309. Min Act: -0.1700
Data Index: 3488668 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8309. Min Act: -0.1700
Data Index: 8327857 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8309. Min Act: -0.1700
Data Index: 7843895 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.8309. Min Act: -0.1700
Data Index: 6184002 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 1542097 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 5592625 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 1154613 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7372. Min Act: -0.1700
Data Index: 2869337 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 6259303 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 6262652 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 6263535 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0184. Min Range: -5.0184
Max Act: 4.7684. Min Act: -0.1700
Data Index: 412981 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19