Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3721 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0002

Data Index: 572095 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0375. Min Act: -0.0002

Data Index: 652132 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0367. Min Act: -0.0002

Data Index: 238301 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0374. Min Act: -0.0002

Data Index: 711673 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0372. Min Act: -0.0002

Data Index: 305940 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0342. Min Act: -0.0002

Data Index: 173090 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0349. Min Act: -0.0002

Data Index: 857537 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0372. Min Act: -0.0002

Data Index: 779220 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0335. Min Act: -0.0002

Data Index: 337976 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0346. Min Act: -0.0002

Data Index: 921116 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0338. Min Act: -0.0002

Data Index: 89184 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1166930 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0336. Min Act: -0.0002

Data Index: 582004 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1501378 (Python Code)

Max Activating Token Index: 40

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1013840 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1028196 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0340. Min Act: -0.0002

Data Index: 457057 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0288. Min Act: -0.0002

Data Index: 783922 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0318. Min Act: -0.0002

Data Index: 141531 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0310. Min Act: -0.0002

Data Index: 395301 (C4 (Web Text))

Max Activating Token Index: 22