Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2657. Min Act: -0.1700
Data Index: 7382816 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2344. Min Act: -0.1700
Data Index: 8327982 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2344. Min Act: -0.1700
Data Index: 7371895 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2344. Min Act: -0.1700
Data Index: 4520372 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2344. Min Act: -0.1700
Data Index: 4460858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2344. Min Act: -0.1700
Data Index: 43284 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2032. Min Act: -0.1700
Data Index: 6837196 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.2032. Min Act: -0.1700
Data Index: 7003343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 6745701 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 14759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 448032 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 480300 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 589123 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 146540 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 2316608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 2376145 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 3789721 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 2904651 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 3274140 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2657. Min Range: -5.2657
Max Act: 5.1719. Min Act: -0.1700
Data Index: 6258016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19