Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3785 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.7710. Min Act: -0.1700
Data Index: 6219491 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.5835. Min Act: -0.1700
Data Index: 7385131 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.3960. Min Act: -0.1700
Data Index: 5780178 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.3335. Min Act: -0.1700
Data Index: 2727878 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.0835. Min Act: -0.1700
Data Index: 3759706 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.0523. Min Act: -0.1700
Data Index: 7866533 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7710. Min Range: -6.7710
Max Act: 6.0210. Min Act: -0.1700
Data Index: 3748415 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.9273. Min Act: -0.1700
Data Index: 6966371 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.9273. Min Act: -0.1700
Data Index: 3447047 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8960. Min Act: -0.1700
Data Index: 1860316 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8648. Min Act: -0.1700
Data Index: 6207576 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8648. Min Act: -0.1700
Data Index: 8065810 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8648. Min Act: -0.1700
Data Index: 7306499 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8648. Min Act: -0.1700
Data Index: 8419290 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8335. Min Act: -0.1700
Data Index: 3706870 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8023. Min Act: -0.1700
Data Index: 815580 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.7710. Min Act: -0.1700
Data Index: 6905201 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8335. Min Act: -0.1700
Data Index: 7253183 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.8023. Min Act: -0.1700
Data Index: 5295585 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7710. Min Range: -6.7710
Max Act: 5.7710. Min Act: -0.1700
Data Index: 6702607 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19