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

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

Neuron 2805 in Layer 3

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: -0.0001

Data Index: 815796 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0315. Min Act: -0.0001

Data Index: 392306 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0334. Min Act: -0.0001

Data Index: 1067726 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1026557 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0342. Min Act: -0.0001

Data Index: 162386 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0321. Min Act: -0.0001

Data Index: 310165 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0296. Min Act: -0.0001

Data Index: 116229 (C4 (Web Text))

Max Activating Token Index: 358

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1203431 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0309. Min Act: -0.0001

Data Index: 878176 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0243. Min Act: -0.0001

Data Index: 185075 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0304. Min Act: -0.0001

Data Index: 629261 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0279. Min Act: -0.0001

Data Index: 432035 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0287. Min Act: -0.0001

Data Index: 932711 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0275. Min Act: -0.0001

Data Index: 804723 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0279. Min Act: -0.0001

Data Index: 367599 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0278. Min Act: -0.0001

Data Index: 302325 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0249. Min Act: -0.0001

Data Index: 185187 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1124271 (C4 (Web Text))

Max Activating Token Index: 615

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0265. Min Act: -0.0001

Data Index: 1487487 (Python Code)

Max Activating Token Index: 78