Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1646 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.9577. Min Act: -0.1700
Data Index: 6372457 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.9577. Min Act: -0.1700
Data Index: 3313070 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3366250 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8639. Min Act: -0.1700
Data Index: 2077103 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8639. Min Act: -0.1700
Data Index: 7457357 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 7457355 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 6296563 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 5868531 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 2605073 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 7457371 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8326. Min Act: -0.1700
Data Index: 2270468 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 2475410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 3783408 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 8595060 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 3371805 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 6903371 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 3675727 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.8013. Min Act: -0.1700
Data Index: 5893360 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.7700. Min Act: -0.1700
Data Index: 1762685 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9577. Min Range: -3.9577
Max Act: 3.7388. Min Act: -0.1700
Data Index: 2199516 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19