Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0469. Min Act: -0.0004

Data Index: 438044 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0422. Min Act: -0.0004

Data Index: 1259949 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0324. Min Act: -0.0004

Data Index: 541905 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0388. Min Act: -0.0004

Data Index: 60606 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0349. Min Act: -0.0004

Data Index: 242053 (C4 (Web Text))

Max Activating Token Index: 311

Text #5

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0382. Min Act: -0.0004

Data Index: 589597 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0358. Min Act: -0.0004

Data Index: 87052 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0365. Min Act: -0.0004

Data Index: 293759 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0396. Min Act: -0.0004

Data Index: 728191 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0333. Min Act: -0.0004

Data Index: 9042 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0303. Min Act: -0.0004

Data Index: 666790 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0359. Min Act: -0.0004

Data Index: 576031 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0350. Min Act: -0.0004

Data Index: 616578 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0363. Min Act: -0.0004

Data Index: 469879 (C4 (Web Text))

Max Activating Token Index: 418

Text #14

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1057002 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0380. Min Act: -0.0004

Data Index: 659554 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1107624 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0356. Min Act: -0.0004

Data Index: 272741 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0338. Min Act: -0.0004

Data Index: 1330889 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.0469. Min Range: -0.0469

Max Act: 0.0350. Min Act: -0.0004

Data Index: 430355 (C4 (Web Text))

Max Activating Token Index: 801