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

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

Neuron 2748 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.4940. Min Act: -0.0000

Data Index: 1218558 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.5128. Min Act: -0.0000

Data Index: 713709 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.4777. Min Act: -0.0000

Data Index: 508817 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.4070. Min Act: -0.0000

Data Index: 107294 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.4022. Min Act: -0.0000

Data Index: 50875 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1105084 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.3656. Min Act: -0.0000

Data Index: 938192 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2543. Min Act: -0.0000

Data Index: 1174969 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.3292. Min Act: -0.0000

Data Index: 1001347 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1325312 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2378. Min Act: -0.0000

Data Index: 488531 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1270205 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2746. Min Act: -0.0000

Data Index: 900874 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1201180 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2607. Min Act: -0.0000

Data Index: 429789 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2341. Min Act: -0.0000

Data Index: 557676 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2214. Min Act: -0.0000

Data Index: 164345 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.1626. Min Act: -0.0000

Data Index: 360338 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.1378. Min Act: -0.0000

Data Index: 980418 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.5128. Min Range: -1.5128

Max Act: 1.2013. Min Act: -0.0000

Data Index: 197398 (C4 (Web Text))

Max Activating Token Index: 680