Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2359 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.3039. Min Act: -0.0001

Data Index: 655852 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.1561. Min Act: -0.0001

Data Index: 443847 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0902. Min Act: -0.0001

Data Index: 55608 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.1180. Min Act: -0.0001

Data Index: 891843 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0160. Min Act: -0.0001

Data Index: 314535 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0205. Min Act: -0.0001

Data Index: 631430 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0436. Min Act: -0.0000

Data Index: 623328 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0550. Min Act: -0.0001

Data Index: 953033 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0334. Min Act: -0.0001

Data Index: 1141101 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0259. Min Act: -0.0001

Data Index: 537660 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9536. Min Act: -0.0001

Data Index: 706099 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 1.3039. Min Range: -1.3039

Max Act: 1.0063. Min Act: -0.0001

Data Index: 429246 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9822. Min Act: -0.0001

Data Index: 497833 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9594. Min Act: -0.0000

Data Index: 263534 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9320. Min Act: -0.0001

Data Index: 91381 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1220920 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9861. Min Act: -0.0001

Data Index: 1198238 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9241. Min Act: -0.0001

Data Index: 1013948 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.3039. Min Range: -1.3039

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1177251 (C4 (Web Text))

Max Activating Token Index: 378