Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2197. Min Range: -3.2197
Max Act: 3.2197. Min Act: -0.1700
Data Index: 151970 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2197. Min Range: -3.2197
Max Act: 3.0307. Min Act: -0.1700
Data Index: 6928993 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9991. Min Act: -0.1700
Data Index: 4477930 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9991. Min Act: -0.1700
Data Index: 8405138 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9517. Min Act: -0.1700
Data Index: 7476190 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9675. Min Act: -0.1700
Data Index: 4445849 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9675. Min Act: -0.1700
Data Index: 8241581 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9675. Min Act: -0.1700
Data Index: 2818054 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9358. Min Act: -0.1700
Data Index: 319058 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9358. Min Act: -0.1700
Data Index: 319059 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9200. Min Act: -0.1700
Data Index: 6620007 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8883. Min Act: -0.1700
Data Index: 8553209 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9041. Min Act: -0.1700
Data Index: 4420457 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8883. Min Act: -0.1700
Data Index: 8724874 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8883. Min Act: -0.1700
Data Index: 4094633 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.9041. Min Act: -0.1700
Data Index: 2189396 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8883. Min Act: -0.1700
Data Index: 4155484 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8724. Min Act: -0.1700
Data Index: 6366389 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8724. Min Act: -0.1700
Data Index: 2444617 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2197. Min Range: -3.2197
Max Act: 2.8565. Min Act: -0.1700
Data Index: 6620008 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19