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

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

Neuron 4207 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8614. Min Act: -0.0001

Data Index: 199836 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8065. Min Act: -0.0001

Data Index: 521543 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1141490 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7930. Min Act: -0.0001

Data Index: 1313079 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8216. Min Act: -0.0001

Data Index: 547915 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7670. Min Act: -0.0001

Data Index: 947605 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7638. Min Act: -0.0001

Data Index: 414377 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7530. Min Act: -0.0001

Data Index: 511815 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7551. Min Act: -0.0001

Data Index: 1222758 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6179. Min Act: -0.0001

Data Index: 554948 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7200. Min Act: -0.0001

Data Index: 1200671 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6841. Min Act: -0.0001

Data Index: 1252447 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6788. Min Act: -0.0001

Data Index: 174388 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6011. Min Act: -0.0001

Data Index: 27734 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6298. Min Act: -0.0001

Data Index: 459384 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6362. Min Act: -0.0001

Data Index: 900355 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6777. Min Act: -0.0001

Data Index: 851690 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6363. Min Act: -0.0001

Data Index: 1195037 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6144. Min Act: -0.0001

Data Index: 964948 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6566. Min Act: -0.0001

Data Index: 61849 (C4 (Web Text))

Max Activating Token Index: 855