Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2715 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.4796. Min Act: -0.0001
Data Index: 708982 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.4640. Min Act: -0.0001
Data Index: 886877 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.4845. Min Act: -0.0001
Data Index: 824550 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3784. Min Act: -0.0001
Data Index: 1148079 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3831. Min Act: -0.0001
Data Index: 39966 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3801. Min Act: -0.0001
Data Index: 192788 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3669. Min Act: -0.0001
Data Index: 911794 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3812. Min Act: -0.0001
Data Index: 1070223 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3580. Min Act: -0.0001
Data Index: 27147 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3408. Min Act: -0.0001
Data Index: 49104 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3860. Min Act: -0.0001
Data Index: 785834 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3996. Min Act: -0.0001
Data Index: 1148213 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3604. Min Act: -0.0001
Data Index: 523577 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3383. Min Act: -0.0001
Data Index: 915071 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3401. Min Act: -0.0001
Data Index: 1277332 (C4 (Web Text))
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3428. Min Act: -0.0001
Data Index: 1246440 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3407. Min Act: -0.0001
Data Index: 45751 (C4 (Web Text))
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3443. Min Act: -0.0001
Data Index: 288060 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3289. Min Act: -0.0001
Data Index: 602083 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4845. Min Range: -0.4845
Max Act: 0.3734. Min Act: -0.0001
Data Index: 598400 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #19