Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2671. Min Act: -0.1700
Data Index: 5996705 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2200. Min Act: -0.1700
Data Index: 2572076 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2200. Min Act: -0.1700
Data Index: 5996718 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2042. Min Act: -0.1700
Data Index: 5996703 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1885. Min Act: -0.1700
Data Index: 5994303 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.2042. Min Act: -0.1700
Data Index: 739057 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1728. Min Act: -0.1700
Data Index: 5710744 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1098. Min Act: -0.1700
Data Index: 5996717 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.1413. Min Act: -0.1700
Data Index: 1555719 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0783. Min Act: -0.1700
Data Index: 2091240 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0940. Min Act: -0.1700
Data Index: 3574648 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0783. Min Act: -0.1700
Data Index: 2299331 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0783. Min Act: -0.1700
Data Index: 1216670 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0625. Min Act: -0.1700
Data Index: 5710726 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0467. Min Act: -0.1700
Data Index: 8796645 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9993. Min Act: -0.1700
Data Index: 2572061 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0309. Min Act: -0.1700
Data Index: 8438234 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2671. Min Range: -3.2671
Max Act: 3.0309. Min Act: -0.1700
Data Index: 5996704 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9993. Min Act: -0.1700
Data Index: 5994304 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2671. Min Range: -3.2671
Max Act: 2.9993. Min Act: -0.1700
Data Index: 5417325 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19