Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 73 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.3473. Min Act: -0.1700
Data Index: 700750 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.3473. Min Act: -0.1700
Data Index: 625166 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2847. Min Act: -0.1700
Data Index: 596250 (C4 (Web Text))
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.3160. Min Act: -0.1700
Data Index: 526840 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2222. Min Act: -0.1700
Data Index: 1240840 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2535. Min Act: -0.1700
Data Index: 527136 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1910. Min Act: -0.1700
Data Index: 1316751 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2222. Min Act: -0.1700
Data Index: 703424 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2222. Min Act: -0.1700
Data Index: 665586 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.2222. Min Act: -0.1700
Data Index: 724760 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1597. Min Act: -0.1700
Data Index: 1166703 (C4 (Web Text))
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1910. Min Act: -0.1700
Data Index: 753525 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1910. Min Act: -0.1700
Data Index: 363210 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1910. Min Act: -0.1700
Data Index: 240465 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1597. Min Act: -0.1700
Data Index: 609194 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1597. Min Act: -0.1700
Data Index: 166557 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1910. Min Act: -0.1700
Data Index: 533775 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1285. Min Act: -0.1700
Data Index: 398724 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1285. Min Act: -0.1700
Data Index: 877846 (C4 (Web Text))
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3473. Min Range: -4.3473
Max Act: 4.1597. Min Act: -0.1700
Data Index: 497889 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19