Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.9458. Min Act: -0.1700
Data Index: 6683677 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.8520. Min Act: -0.1700
Data Index: 1280211 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.8208. Min Act: -0.1700
Data Index: 6505115 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.8208. Min Act: -0.1700
Data Index: 8025535 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7895. Min Act: -0.1700
Data Index: 3501192 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7895. Min Act: -0.1700
Data Index: 1578288 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.8208. Min Act: -0.1700
Data Index: 1423862 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7583. Min Act: -0.1700
Data Index: 7688413 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7583. Min Act: -0.1699
Data Index: 5489437 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7583. Min Act: -0.1700
Data Index: 6263507 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1700
Data Index: 6320115 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1700
Data Index: 443109 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1687
Data Index: 110927 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1700
Data Index: 8012975 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1700
Data Index: 1657510 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.7270. Min Act: -0.1700
Data Index: 421584 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.6958. Min Act: -0.1699
Data Index: 7224846 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.6958. Min Act: -0.1700
Data Index: 4974897 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.6645. Min Act: -0.1700
Data Index: 1211600 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9458. Min Range: -5.9458
Max Act: 5.6645. Min Act: -0.1700
Data Index: 740785 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19