Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.7596. Min Act: -0.1700
Data Index: 7023425 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.5721. Min Act: -0.1700
Data Index: 8292591 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.5096. Min Act: -0.1700
Data Index: 8533616 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.4471. Min Act: -0.1700
Data Index: 8533551 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.4471. Min Act: -0.1700
Data Index: 6394620 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.4471. Min Act: -0.1700
Data Index: 3285681 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.4471. Min Act: -0.1700
Data Index: 4870199 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.3534. Min Act: -0.1700
Data Index: 4319225 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.3534. Min Act: -0.1700
Data Index: 8481527 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.3221. Min Act: -0.1700
Data Index: 638054 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.2284. Min Act: -0.1700
Data Index: 5277879 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.2284. Min Act: -0.1700
Data Index: 2247454 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.2284. Min Act: -0.1700
Data Index: 3647042 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.2596. Min Act: -0.1700
Data Index: 1358463 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.1971. Min Act: -0.1700
Data Index: 2485854 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.1971. Min Act: -0.1700
Data Index: 3697387 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.1971. Min Act: -0.1700
Data Index: 583 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.2284. Min Act: -0.1700
Data Index: 5918958 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.1659. Min Act: -0.1700
Data Index: 7169603 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7596. Min Range: -7.7596
Max Act: 7.1659. Min Act: -0.1700
Data Index: 2295297 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19