Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.9733. Min Act: -0.1700
Data Index: 3843995 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.9108. Min Act: -0.1700
Data Index: 7415591 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.8482. Min Act: -0.1700
Data Index: 8112057 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.8013. Min Act: -0.1700
Data Index: 4103712 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.7857. Min Act: -0.1700
Data Index: 7987836 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6919. Min Act: -0.1700
Data Index: 2407382 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6762. Min Act: -0.1700
Data Index: 5450127 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6762. Min Act: -0.1700
Data Index: 6925000 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6606. Min Act: -0.1700
Data Index: 4556466 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6606. Min Act: -0.1700
Data Index: 3340118 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6449. Min Act: -0.1700
Data Index: 1397374 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6293. Min Act: -0.1700
Data Index: 610254 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6136. Min Act: -0.1700
Data Index: 7684748 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6293. Min Act: -0.1700
Data Index: 6256713 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.5980. Min Act: -0.1700
Data Index: 8175186 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.5980. Min Act: -0.1700
Data Index: 6525440 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.5980. Min Act: -0.1700
Data Index: 1455387 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.5823. Min Act: -0.1700
Data Index: 3384042 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.6136. Min Act: -0.1700
Data Index: 5909441 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9733. Min Range: -3.9733
Max Act: 3.5823. Min Act: -0.1700
Data Index: 2653203 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19