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

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

Neuron 2443 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1528572 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1253281 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1359269 (C4 (Web Text))

Max Activating Token Index: 325

Text #4

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5172. Min Act: -0.0000

Data Index: 867410 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1524477 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1052555 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1089243 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5350. Min Act: -0.0000

Data Index: 1386027 (Python Code)

Max Activating Token Index: 82

Text #9

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1411340 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1547742 (Python Code)

Max Activating Token Index: 889

Text #11

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5054. Min Act: -0.0000

Data Index: 1433825 (Python Code)

Max Activating Token Index: 586

Text #12

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1495497 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1365611 (Python Code)

Max Activating Token Index: 158

Text #14

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5320. Min Act: -0.0000

Data Index: 71871 (C4 (Web Text))

Max Activating Token Index: 516

Text #15

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1503518 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1508028 (Python Code)

Max Activating Token Index: 960

Text #17

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.4847. Min Act: -0.0000

Data Index: 1575927 (Python Code)

Max Activating Token Index: 118

Text #18

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.5049. Min Act: -0.0000

Data Index: 201589 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.8116. Min Range: -0.8116

Max Act: 0.4309. Min Act: -0.0000

Data Index: 541681 (C4 (Web Text))

Max Activating Token Index: 661