Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1214. Min Range: -8.1214
Max Act: 8.1214. Min Act: -0.1700
Data Index: 1950991 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.9339. Min Act: -0.1700
Data Index: 974505 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.7464. Min Act: -0.1700
Data Index: 1690710 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.6839. Min Act: -0.1700
Data Index: 7891162 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.5902. Min Act: -0.1700
Data Index: 7005469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.5589. Min Act: -0.1700
Data Index: 3078131 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.5589. Min Act: -0.1700
Data Index: 7385390 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.5589. Min Act: -0.1700
Data Index: 1016493 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4964. Min Act: -0.1700
Data Index: 7152864 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4652. Min Act: -0.1700
Data Index: 1734795 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4964. Min Act: -0.1700
Data Index: 591389 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4964. Min Act: -0.1700
Data Index: 4986187 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4027. Min Act: -0.1700
Data Index: 7614978 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4652. Min Act: -0.1700
Data Index: 7538381 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4339. Min Act: -0.1700
Data Index: 502084 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.3714. Min Act: -0.1700
Data Index: 6283114 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.4027. Min Act: -0.1700
Data Index: 8523237 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.3714. Min Act: -0.1700
Data Index: 3638567 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.3714. Min Act: -0.1700
Data Index: 1185135 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1214. Min Range: -8.1214
Max Act: 7.3402. Min Act: -0.1700
Data Index: 2019619 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19