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

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

Neuron 2787 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5160. Min Act: -0.0001

Data Index: 1544371 (Python Code)

Max Activating Token Index: 85

Text #1

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5164. Min Act: -0.0001

Data Index: 1527559 (Python Code)

Max Activating Token Index: 71

Text #2

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5200. Min Act: -0.0001

Data Index: 1371440 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5164. Min Act: -0.0001

Data Index: 1630344 (Python Code)

Max Activating Token Index: 256

Text #4

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.5222. Min Act: -0.0001

Data Index: 1423211 (Python Code)

Max Activating Token Index: 411

Text #5

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4868. Min Act: -0.0001

Data Index: 1452462 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4994. Min Act: -0.0001

Data Index: 1392255 (Python Code)

Max Activating Token Index: 407

Text #7

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4848. Min Act: -0.0001

Data Index: 1375606 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4809. Min Act: -0.0001

Data Index: 1479665 (Python Code)

Max Activating Token Index: 32

Text #9

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1570176 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4843. Min Act: -0.0001

Data Index: 1378020 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4808. Min Act: -0.0001

Data Index: 1360874 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4624. Min Act: -0.0002

Data Index: 1366718 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4616. Min Act: -0.0001

Data Index: 1499371 (Python Code)

Max Activating Token Index: 201

Text #14

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4476. Min Act: -0.0001

Data Index: 1642716 (Python Code)

Max Activating Token Index: 85

Text #15

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4713. Min Act: -0.0001

Data Index: 1516472 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1535618 (Python Code)

Max Activating Token Index: 346

Text #17

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4733. Min Act: -0.0001

Data Index: 1431649 (Python Code)

Max Activating Token Index: 186

Text #18

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1451658 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.5222. Min Range: -0.5222

Max Act: 0.4669. Min Act: -0.0001

Data Index: 1610125 (Python Code)

Max Activating Token Index: 639