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

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

Neuron 3542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1301206 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3067. Min Act: -0.0000

Data Index: 1210387 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3392. Min Act: -0.0000

Data Index: 1016233 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3362. Min Act: -0.0000

Data Index: 81390 (C4 (Web Text))

Max Activating Token Index: 361

Text #4

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3254. Min Act: -0.0000

Data Index: 1116486 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1316449 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2994. Min Act: -0.0000

Data Index: 867988 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2804. Min Act: -0.0000

Data Index: 368596 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2949. Min Act: -0.0000

Data Index: 235312 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3043. Min Act: -0.0000

Data Index: 60241 (C4 (Web Text))

Max Activating Token Index: 13

Text #10

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.3249. Min Act: -0.0000

Data Index: 95963 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2756. Min Act: -0.0000

Data Index: 415645 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1220602 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2879. Min Act: -0.0000

Data Index: 381089 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2768. Min Act: -0.0000

Data Index: 893368 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2861. Min Act: -0.0000

Data Index: 424085 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2854. Min Act: -0.0000

Data Index: 352429 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2839. Min Act: -0.0000

Data Index: 527424 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2807. Min Act: -0.0000

Data Index: 88465 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 0.3392. Min Range: -0.3392

Max Act: 0.2981. Min Act: -0.0000

Data Index: 222447 (C4 (Web Text))

Max Activating Token Index: 839