Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2338 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0771. Min Range: -4.0771
Max Act: 4.0771. Min Act: -0.1700
Data Index: 2556416 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0771. Min Range: -4.0771
Max Act: 4.0771. Min Act: -0.1700
Data Index: 6671682 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0771. Min Range: -4.0771
Max Act: 4.0459. Min Act: -0.1700
Data Index: 1819099 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0771. Min Range: -4.0771
Max Act: 4.0459. Min Act: -0.1700
Data Index: 7729546 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9834. Min Act: -0.1700
Data Index: 7038441 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9834. Min Act: -0.1700
Data Index: 7949406 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9521. Min Act: -0.1700
Data Index: 8540375 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9834. Min Act: -0.1700
Data Index: 6278510 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9521. Min Act: -0.1700
Data Index: 887457 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9521. Min Act: -0.1700
Data Index: 7751421 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8896. Min Act: -0.1700
Data Index: 5292549 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9208. Min Act: -0.1700
Data Index: 7751422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9208. Min Act: -0.1700
Data Index: 622062 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9208. Min Act: -0.1700
Data Index: 6877172 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.9208. Min Act: -0.1700
Data Index: 736508 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8896. Min Act: -0.1700
Data Index: 8730075 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8896. Min Act: -0.1700
Data Index: 6428659 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8896. Min Act: -0.1700
Data Index: 6363148 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8896. Min Act: -0.1700
Data Index: 7497824 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0771. Min Range: -4.0771
Max Act: 3.8583. Min Act: -0.1700
Data Index: 3533900 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19