Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.6314. Min Act: -0.1700
Data Index: 7423472 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.3502. Min Act: -0.1700
Data Index: 100748 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.2877. Min Act: -0.1700
Data Index: 7240276 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.2252. Min Act: -0.1700
Data Index: 7423473 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.1939. Min Act: -0.1700
Data Index: 8607515 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.1002. Min Act: -0.1700
Data Index: 1133447 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 719000 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 3988697 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0377. Min Act: -0.1700
Data Index: 3899592 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 7167885 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9752. Min Act: -0.1700
Data Index: 7240274 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6314. Min Range: -5.6314
Max Act: 5.0064. Min Act: -0.1700
Data Index: 4394228 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 1769691 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 7240264 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9127. Min Act: -0.1700
Data Index: 3712433 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9127. Min Act: -0.1700
Data Index: 7472819 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.9439. Min Act: -0.1700
Data Index: 8445349 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 1523827 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 4264270 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6314. Min Range: -5.6314
Max Act: 4.8814. Min Act: -0.1700
Data Index: 7240263 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19