Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1630 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.4825. Min Act: -0.0000

Data Index: 680107 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1320679 (C4 (Web Text))

Max Activating Token Index: 430

Text #2

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.4641. Min Act: -0.0000

Data Index: 1350278 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.4071. Min Act: -0.0000

Data Index: 1199505 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3874. Min Act: -0.0000

Data Index: 601392 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3994. Min Act: -0.0000

Data Index: 1119013 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3428. Min Act: -0.0000

Data Index: 63864 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3347. Min Act: -0.0000

Data Index: 176502 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3171. Min Act: -0.0000

Data Index: 619003 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2858. Min Act: -0.0000

Data Index: 790635 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1333464 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1045164 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2757. Min Act: -0.0000

Data Index: 845534 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1071219 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2734. Min Act: -0.0000

Data Index: 836498 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2479. Min Act: -0.0000

Data Index: 633396 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2486. Min Act: -0.0000

Data Index: 455333 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2570. Min Act: -0.0000

Data Index: 963701 (C4 (Web Text))

Max Activating Token Index: 530

Text #18

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1076924 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.4825. Min Range: -0.4825

Max Act: 0.2505. Min Act: -0.0000

Data Index: 767792 (C4 (Web Text))

Max Activating Token Index: 392