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

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

Neuron 580 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1226953 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.6089. Min Act: -0.0000

Data Index: 978892 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5346. Min Act: -0.0000

Data Index: 922583 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5490. Min Act: -0.0000

Data Index: 726946 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5490. Min Act: -0.0000

Data Index: 646718 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5446. Min Act: -0.0000

Data Index: 388608 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5541. Min Act: -0.0000

Data Index: 325253 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1184737 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5362. Min Act: -0.0000

Data Index: 325292 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4958. Min Act: -0.0000

Data Index: 48187 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4948. Min Act: -0.0000

Data Index: 266207 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5107. Min Act: -0.0000

Data Index: 657149 (C4 (Web Text))

Max Activating Token Index: 101

Text #12

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1259678 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4930. Min Act: -0.0000

Data Index: 1227167 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4642. Min Act: -0.0000

Data Index: 354760 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4810. Min Act: -0.0000

Data Index: 425228 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1201996 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4615. Min Act: -0.0000

Data Index: 356789 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1249027 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.7131. Min Range: -0.7131

Max Act: 0.4495. Min Act: -0.0000

Data Index: 903230 (C4 (Web Text))

Max Activating Token Index: 193