Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.1173. Min Act: -0.1700
Data Index: 8423126 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.1173. Min Act: -0.1700
Data Index: 4728893 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.0860. Min Act: -0.1700
Data Index: 900023 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1173. Min Range: -6.1173
Max Act: 6.0235. Min Act: -0.1700
Data Index: 7616589 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.9610. Min Act: -0.1700
Data Index: 8254408 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 2959713 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8985. Min Act: -0.1700
Data Index: 4634760 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 8427434 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8360. Min Act: -0.1700
Data Index: 1404647 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8673. Min Act: -0.1700
Data Index: 6419992 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8048. Min Act: -0.1700
Data Index: 2856475 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8360. Min Act: -0.1700
Data Index: 848623 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 508503 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 7035691 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3509446 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.8048. Min Act: -0.1700
Data Index: 7130191 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1186582 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 5254838 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7735. Min Act: -0.1700
Data Index: 3363535 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1173. Min Range: -6.1173
Max Act: 5.7110. Min Act: -0.1700
Data Index: 192086 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19