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

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

Neuron 4776 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2968. Min Act: -0.0000

Data Index: 464421 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.3690. Min Act: -0.0000

Data Index: 530803 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.4164. Min Act: -0.0000

Data Index: 63679 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1209550 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1776. Min Act: -0.0000

Data Index: 162327 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1170748 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9581. Min Act: -0.0000

Data Index: 185348 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0283. Min Act: -0.0000

Data Index: 368695 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1257. Min Act: -0.0000

Data Index: 147251 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.1021. Min Act: -0.0000

Data Index: 476014 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1338630 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0261. Min Act: -0.0000

Data Index: 413716 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0720. Min Act: -0.0000

Data Index: 550295 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9455. Min Act: -0.0000

Data Index: 1470222 (Python Code)

Max Activating Token Index: 311

Text #14

Max Range: 1.4164. Min Range: -1.4164

Max Act: 1.0524. Min Act: -0.0000

Data Index: 921460 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.8982. Min Act: -0.0000

Data Index: 109516 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1403388 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9360. Min Act: -0.0000

Data Index: 136111 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1247165 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.4164. Min Range: -1.4164

Max Act: 0.8449. Min Act: -0.0000

Data Index: 343327 (C4 (Web Text))

Max Activating Token Index: 182