Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1601 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.9908. Min Act: -0.1700
Data Index: 5315751 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.8971. Min Act: -0.1700
Data Index: 8686628 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.7408. Min Act: -0.1700
Data Index: 7703232 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.7096. Min Act: -0.1700
Data Index: 8637476 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.6783. Min Act: -0.1700
Data Index: 473227 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5846. Min Act: -0.1700
Data Index: 269875 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5846. Min Act: -0.1700
Data Index: 1335964 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5846. Min Act: -0.1700
Data Index: 3960909 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5846. Min Act: -0.1700
Data Index: 3956976 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5221. Min Act: -0.1700
Data Index: 2971984 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5533. Min Act: -0.1700
Data Index: 3122409 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5533. Min Act: -0.1700
Data Index: 8547896 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5221. Min Act: -0.1700
Data Index: 2458588 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.5221. Min Act: -0.1700
Data Index: 3825548 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4908. Min Act: -0.1700
Data Index: 864080 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4596. Min Act: -0.1700
Data Index: 5140384 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4908. Min Act: -0.1700
Data Index: 890006 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4596. Min Act: -0.1700
Data Index: 6612910 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4908. Min Act: -0.1700
Data Index: 4940634 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9908. Min Range: -4.9908
Max Act: 4.4596. Min Act: -0.1700
Data Index: 3153137 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19