Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4173 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.8920. Min Act: -0.1700
Data Index: 2636058 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.8607. Min Act: -0.1700
Data Index: 832433 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.8295. Min Act: -0.1700
Data Index: 3174638 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.7982. Min Act: -0.1700
Data Index: 594203 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.7045. Min Act: -0.1700
Data Index: 7902844 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.6732. Min Act: -0.1700
Data Index: 6117544 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.6732. Min Act: -0.1700
Data Index: 4086684 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.6420. Min Act: -0.1700
Data Index: 8733470 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.6107. Min Act: -0.1700
Data Index: 6680231 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.5795. Min Act: -0.1700
Data Index: 793320 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.5795. Min Act: -0.1700
Data Index: 7343408 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.5482. Min Act: -0.1700
Data Index: 5322514 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.4857. Min Act: -0.1700
Data Index: 330099 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.4857. Min Act: -0.1700
Data Index: 1988456 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.4545. Min Act: -0.1700
Data Index: 6567883 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.3920. Min Act: -0.1700
Data Index: 1322628 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.4232. Min Act: -0.1700
Data Index: 6735579 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.4232. Min Act: -0.1700
Data Index: 4010298 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.3920. Min Act: -0.1700
Data Index: 1205185 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8920. Min Range: -6.8920
Max Act: 6.3920. Min Act: -0.1700
Data Index: 3038743 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19