Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.5405. Min Act: -0.1700
Data Index: 4150376 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.4467. Min Act: -0.1700
Data Index: 7095268 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.3842. Min Act: -0.1700
Data Index: 3901765 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.3842. Min Act: -0.1700
Data Index: 5328012 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.2905. Min Act: -0.1700
Data Index: 6688343 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.3217. Min Act: -0.1700
Data Index: 1704096 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.2592. Min Act: -0.1700
Data Index: 3035788 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.2592. Min Act: -0.1700
Data Index: 1683585 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5958624 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5600512 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1700
Data Index: 7091329 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1655. Min Act: -0.1700
Data Index: 4681310 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1655. Min Act: -0.1699
Data Index: 4341147 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1696
Data Index: 1439660 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5964941 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1700
Data Index: 8073158 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1700
Data Index: 270654 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1030. Min Act: -0.1700
Data Index: 17797 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.1342. Min Act: -0.1700
Data Index: 5453317 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5405. Min Range: -6.5405
Max Act: 6.0717. Min Act: -0.1700
Data Index: 1699040 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19