Model: GELU Model: 2 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 781 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')
Text #0
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9850. Min Act: -0.1700
Data Index: 943450 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9765. Min Act: -0.1700
Data Index: 434677 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1700
Data Index: 1428979 (Python Code)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9596. Min Act: -0.1700
Data Index: 1315401 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9596. Min Act: -0.1700
Data Index: 1062193 (C4 (Web Text))
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9681. Min Act: -0.1700
Data Index: 724287 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1700
Data Index: 1176499 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1700
Data Index: 166586 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1700
Data Index: 940200 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1700
Data Index: 1045685 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9426. Min Act: -0.1700
Data Index: 1085058 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9426. Min Act: -0.1700
Data Index: 268518 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9511. Min Act: -0.1698
Data Index: 1467795 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9341. Min Act: -0.1700
Data Index: 752394 (C4 (Web Text))
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9341. Min Act: -0.1700
Data Index: 1176390 (C4 (Web Text))
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9426. Min Act: -0.1700
Data Index: 171258 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9256. Min Act: -0.1700
Data Index: 143482 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9341. Min Act: -0.1700
Data Index: 939604 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9256. Min Act: -0.1700
Data Index: 1061608 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9850. Min Range: -1.9850
Max Act: 1.9341. Min Act: -0.1700
Data Index: 350755 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19