Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4993 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.2194. Min Act: -0.1700
Data Index: 2922477 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0631. Min Act: -0.1700
Data Index: 1867289 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0631. Min Act: -0.1700
Data Index: 1989280 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0319. Min Act: -0.1700
Data Index: 4354586 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2194. Min Range: -6.2194
Max Act: 6.0319. Min Act: -0.1700
Data Index: 6652941 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 8248642 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 1655184 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 4649190 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 7941935 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9694. Min Act: -0.1700
Data Index: 6682494 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9381. Min Act: -0.1700
Data Index: 7446799 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8756. Min Act: -0.1700
Data Index: 1659220 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 5556402 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 6938912 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3717398 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 3241928 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.9069. Min Act: -0.1700
Data Index: 1808001 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8756. Min Act: -0.1700
Data Index: 3565461 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8756. Min Act: -0.1700
Data Index: 2613166 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2194. Min Range: -6.2194
Max Act: 5.8444. Min Act: -0.1700
Data Index: 7734848 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #19