Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.9817. Min Act: -0.1700
Data Index: 8456611 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.8879. Min Act: -0.1700
Data Index: 7287037 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.7942. Min Act: -0.1700
Data Index: 8149783 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.7942. Min Act: -0.1700
Data Index: 4698976 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.7629. Min Act: -0.1700
Data Index: 5580008 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.8254. Min Act: -0.1700
Data Index: 7287039 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.8254. Min Act: -0.1700
Data Index: 3428068 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.7317. Min Act: -0.1700
Data Index: 6462499 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.7629. Min Act: -0.1700
Data Index: 6462497 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.6692. Min Act: -0.1700
Data Index: 5580007 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5754. Min Act: -0.1700
Data Index: 4425802 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5754. Min Act: -0.1700
Data Index: 7984774 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.6067. Min Act: -0.1700
Data Index: 396024 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 7051807 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5442. Min Act: -0.1700
Data Index: 5467327 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5754. Min Act: -0.1700
Data Index: 1058538 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5442. Min Act: -0.1700
Data Index: 3341072 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5129. Min Act: -0.1700
Data Index: 4425803 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.4192. Min Act: -0.1700
Data Index: 880097 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9817. Min Range: -5.9817
Max Act: 5.5129. Min Act: -0.1700
Data Index: 965126 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19