Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5658 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.7089. Min Act: -0.1700
Data Index: 5744487 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.2402. Min Act: -0.1700
Data Index: 1342938 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.2089. Min Act: -0.1700
Data Index: 1468792 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1777. Min Act: -0.1700
Data Index: 2977989 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1777. Min Act: -0.1700
Data Index: 5823446 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1777. Min Act: -0.1700
Data Index: 4345397 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1464. Min Act: -0.1700
Data Index: 7678994 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1152. Min Act: -0.1700
Data Index: 5226217 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1152. Min Act: -0.1700
Data Index: 4345396 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.1464. Min Act: -0.1700
Data Index: 7098229 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0839. Min Act: -0.1700
Data Index: 5188554 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0527. Min Act: -0.1700
Data Index: 2421898 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0527. Min Act: -0.1700
Data Index: 7225737 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0527. Min Act: -0.1700
Data Index: 7118504 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0527. Min Act: -0.1700
Data Index: 2228138 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0214. Min Act: -0.1700
Data Index: 4025641 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0214. Min Act: -0.1700
Data Index: 4326822 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2104344 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0214. Min Act: -0.1700
Data Index: 3255149 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7089. Min Range: -6.7089
Max Act: 6.0214. Min Act: -0.1700
Data Index: 2078388 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19