Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2070 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.2795. Min Act: -0.1700
Data Index: 1655499 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.2170. Min Act: -0.1700
Data Index: 3901263 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 7382152 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.2170. Min Act: -0.1700
Data Index: 3948164 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 1951976 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 8091285 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 8621537 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1858. Min Act: -0.1700
Data Index: 6265227 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1545. Min Act: -0.1700
Data Index: 7502489 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.1233. Min Act: -0.1700
Data Index: 1235641 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0920. Min Act: -0.1700
Data Index: 933136 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0608. Min Act: -0.1700
Data Index: 1783300 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0608. Min Act: -0.1700
Data Index: 6253978 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0608. Min Act: -0.1700
Data Index: 2222427 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0608. Min Act: -0.1700
Data Index: 8091284 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0295. Min Act: -0.1700
Data Index: 2581242 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0295. Min Act: -0.1700
Data Index: 727838 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0295. Min Act: -0.1700
Data Index: 5368461 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0295. Min Act: -0.1700
Data Index: 2487558 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2795. Min Range: -7.2795
Max Act: 7.0295. Min Act: -0.1700
Data Index: 4417986 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19