Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1702 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0556. Min Range: -6.0556
Max Act: 6.0556. Min Act: -0.1700
Data Index: 3805629 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0556. Min Range: -6.0556
Max Act: 6.0244. Min Act: -0.1700
Data Index: 3759345 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0556. Min Range: -6.0556
Max Act: 6.0244. Min Act: -0.1700
Data Index: 7616557 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8994. Min Act: -0.1700
Data Index: 4719931 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.9306. Min Act: -0.1700
Data Index: 3195553 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.8056. Min Act: -0.1700
Data Index: 7628863 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7431. Min Act: -0.1700
Data Index: 3282749 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7431. Min Act: -0.1700
Data Index: 6721251 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7119. Min Act: -0.1700
Data Index: 1011302 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6806. Min Act: -0.1700
Data Index: 1232807 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.7119. Min Act: -0.1700
Data Index: 8266722 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6806. Min Act: -0.1700
Data Index: 4708226 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6494. Min Act: -0.1700
Data Index: 4219910 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6494. Min Act: -0.1700
Data Index: 4350899 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1708191 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1905215 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.5244. Min Act: -0.1700
Data Index: 4219908 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.4931. Min Act: -0.1700
Data Index: 5255761 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.4931. Min Act: -0.1700
Data Index: 76451 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0556. Min Range: -6.0556
Max Act: 5.4931. Min Act: -0.1700
Data Index: 3566524 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19