Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2610 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4199. Min Range: -4.4199
Max Act: 4.4199. Min Act: -0.1700
Data Index: 1125275 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4199. Min Range: -4.4199
Max Act: 4.1074. Min Act: -0.1700
Data Index: 5898881 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4199. Min Range: -4.4199
Max Act: 4.0448. Min Act: -0.1700
Data Index: 1755051 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4199. Min Range: -4.4199
Max Act: 4.0761. Min Act: -0.1700
Data Index: 5061461 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4199. Min Range: -4.4199
Max Act: 4.0448. Min Act: -0.1700
Data Index: 7197258 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8658224 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 448457 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 8484886 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 2612465 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7548927 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9823. Min Act: -0.1700
Data Index: 7800375 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9511. Min Act: -0.1700
Data Index: 5757518 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9198. Min Act: -0.1700
Data Index: 2565538 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.9198. Min Act: -0.1700
Data Index: 7854335 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.8260. Min Act: -0.1700
Data Index: 6835470 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.8104. Min Act: -0.1700
Data Index: 2715241 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.8104. Min Act: -0.1700
Data Index: 4713913 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.8104. Min Act: -0.1700
Data Index: 522892 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.8104. Min Act: -0.1700
Data Index: 875653 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4199. Min Range: -4.4199
Max Act: 3.7791. Min Act: -0.1700
Data Index: 5551349 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19