Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3468 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.4504. Min Act: -0.1700
Data Index: 5216565 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.2936. Min Act: -0.1700
Data Index: 8692826 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.2308. Min Act: -0.1700
Data Index: 365380 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1836. Min Act: -0.1700
Data Index: 3405380 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1836. Min Act: -0.1700
Data Index: 957846 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1679. Min Act: -0.1700
Data Index: 4074089 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1679. Min Act: -0.1700
Data Index: 640538 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1679. Min Act: -0.1700
Data Index: 7586930 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1364. Min Act: -0.1700
Data Index: 5118288 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1364. Min Act: -0.1700
Data Index: 640539 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1364. Min Act: -0.1700
Data Index: 4705995 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1206. Min Act: -0.1700
Data Index: 4120014 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1206. Min Act: -0.1700
Data Index: 4620875 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1206. Min Act: -0.1700
Data Index: 3845200 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1206. Min Act: -0.1700
Data Index: 46728 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1049. Min Act: -0.1700
Data Index: 5831510 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1049. Min Act: -0.1700
Data Index: 8413874 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1049. Min Act: -0.1700
Data Index: 5674149 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.1049. Min Act: -0.1700
Data Index: 745951 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4504. Min Range: -3.4504
Max Act: 3.0891. Min Act: -0.1700
Data Index: 5065889 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19