Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2803. Min Range: -5.2803
Max Act: 5.2803. Min Act: -0.1700
Data Index: 929373 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2803. Min Range: -5.2803
Max Act: 5.1865. Min Act: -0.1700
Data Index: 3945673 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2803. Min Range: -5.2803
Max Act: 5.1865. Min Act: -0.1700
Data Index: 5596711 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9990. Min Act: -0.1700
Data Index: 3915825 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9678. Min Act: -0.1700
Data Index: 4589215 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9678. Min Act: -0.1700
Data Index: 1816939 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9678. Min Act: -0.1700
Data Index: 2898318 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9678. Min Act: -0.1700
Data Index: 8170046 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9365. Min Act: -0.1700
Data Index: 2865104 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.9053. Min Act: -0.1700
Data Index: 8547827 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8740. Min Act: -0.1700
Data Index: 1626044 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8740. Min Act: -0.1700
Data Index: 1563364 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8740. Min Act: -0.1700
Data Index: 960645 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8740. Min Act: -0.1700
Data Index: 1529420 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8428. Min Act: -0.1700
Data Index: 3962883 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8740. Min Act: -0.1700
Data Index: 3288840 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8115. Min Act: -0.1700
Data Index: 4322297 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8428. Min Act: -0.1700
Data Index: 5308537 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8428. Min Act: -0.1700
Data Index: 1663089 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2803. Min Range: -5.2803
Max Act: 4.8115. Min Act: -0.1700
Data Index: 6975263 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #19