Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 397 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2361. Min Range: -3.2361
Max Act: 3.2361. Min Act: -0.1700
Data Index: 762310 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2361. Min Range: -3.2361
Max Act: 3.0629. Min Act: -0.1700
Data Index: 1158007 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2361. Min Range: -3.2361
Max Act: 3.0629. Min Act: -0.1700
Data Index: 331308 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9681. Min Act: -0.1700
Data Index: 1307209 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9364. Min Act: -0.1700
Data Index: 915124 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2361. Min Range: -3.2361
Max Act: 3.0155. Min Act: -0.1700
Data Index: 523446 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9681. Min Act: -0.1700
Data Index: 828744 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9364. Min Act: -0.1700
Data Index: 245750 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8888. Min Act: -0.1700
Data Index: 509496 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8888. Min Act: -0.1700
Data Index: 325683 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8888. Min Act: -0.1700
Data Index: 316426 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9047. Min Act: -0.1700
Data Index: 717663 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.9364. Min Act: -0.1700
Data Index: 683185 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8571. Min Act: -0.1700
Data Index: 443507 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8730. Min Act: -0.1700
Data Index: 320980 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8571. Min Act: -0.1700
Data Index: 640106 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8571. Min Act: -0.1700
Data Index: 502826 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8412. Min Act: -0.1700
Data Index: 878530 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8888. Min Act: -0.1700
Data Index: 250575 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2361. Min Range: -3.2361
Max Act: 2.8412. Min Act: -0.1700
Data Index: 935534 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19