Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 897 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.5329. Min Act: -0.1700
Data Index: 3349737 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.4392. Min Act: -0.1700
Data Index: 2961880 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.4392. Min Act: -0.1700
Data Index: 8380189 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.3767. Min Act: -0.1700
Data Index: 6633742 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.3767. Min Act: -0.1700
Data Index: 955743 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.4079. Min Act: -0.1700
Data Index: 5552021 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.3767. Min Act: -0.1700
Data Index: 4752881 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.3454. Min Act: -0.1700
Data Index: 5660895 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.3142. Min Act: -0.1700
Data Index: 553674 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.2829. Min Act: -0.1700
Data Index: 2025068 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.2204. Min Act: -0.1700
Data Index: 4187531 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1892. Min Act: -0.1700
Data Index: 6428430 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 1831681 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 8796432 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 3381254 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 8605663 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 4118160 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.0954. Min Act: -0.1700
Data Index: 8049068 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 7902568 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5329. Min Range: -5.5329
Max Act: 5.1267. Min Act: -0.1700
Data Index: 4659806 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19