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

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

Neuron 2423 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0597. Min Act: -0.0001

Data Index: 838887 (C4 (Web Text))

Max Activating Token Index: 4

Text #1

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0535. Min Act: -0.0001

Data Index: 737138 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0557. Min Act: -0.0001

Data Index: 35153 (C4 (Web Text))

Max Activating Token Index: 711

Text #3

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0478. Min Act: -0.0001

Data Index: 361894 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0504. Min Act: -0.0001

Data Index: 718436 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0474. Min Act: -0.0001

Data Index: 811990 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0428. Min Act: -0.0000

Data Index: 251708 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0436. Min Act: -0.0000

Data Index: 506005 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0472. Min Act: -0.0001

Data Index: 127209 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0431. Min Act: -0.0001

Data Index: 231260 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0427. Min Act: -0.0001

Data Index: 678213 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1022343 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0444. Min Act: -0.0000

Data Index: 365212 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0413. Min Act: -0.0001

Data Index: 647722 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0408. Min Act: -0.0001

Data Index: 163304 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0404. Min Act: -0.0000

Data Index: 626329 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0369. Min Act: -0.0000

Data Index: 824991 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0414. Min Act: -0.0000

Data Index: 480606 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0382. Min Act: -0.0000

Data Index: 670566 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.0597. Min Range: -0.0597

Max Act: 0.0398. Min Act: -0.0001

Data Index: 274996 (C4 (Web Text))

Max Activating Token Index: 1013