Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2947 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.7203. Min Act: -0.1700
Data Index: 6431722 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.6891. Min Act: -0.1700
Data Index: 5282997 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.6578. Min Act: -0.1700
Data Index: 7540046 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5641. Min Act: -0.1700
Data Index: 8132056 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5953. Min Act: -0.1700
Data Index: 2094791 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5641. Min Act: -0.1700
Data Index: 6296686 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5641. Min Act: -0.1700
Data Index: 4689644 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5328. Min Act: -0.1700
Data Index: 46580 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5328. Min Act: -0.1700
Data Index: 5138544 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5016. Min Act: -0.1700
Data Index: 2912000 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4703. Min Act: -0.1700
Data Index: 7280545 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5016. Min Act: -0.1700
Data Index: 1996607 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5016. Min Act: -0.1700
Data Index: 7627222 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4703. Min Act: -0.1700
Data Index: 1393419 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5016. Min Act: -0.1700
Data Index: 1313318 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4391. Min Act: -0.1700
Data Index: 8069578 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4703. Min Act: -0.1700
Data Index: 604380 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.5016. Min Act: -0.1700
Data Index: 6356776 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4703. Min Act: -0.1700
Data Index: 7024531 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7203. Min Range: -4.7203
Max Act: 4.4078. Min Act: -0.1700
Data Index: 936681 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19