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

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

Neuron 4820 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: 2.9450. Min Range: -2.9450

Max Act: 2.9450. Min Act: -0.0000

Data Index: 779721 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.8563. Min Act: -0.0000

Data Index: 409036 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.4675. Min Act: -0.0000

Data Index: 1143499 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.5823. Min Act: -0.0000

Data Index: 33349 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.5022. Min Act: -0.0000

Data Index: 76363 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.3880. Min Act: -0.0000

Data Index: 250714 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.4468. Min Act: -0.0000

Data Index: 651264 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.2287. Min Act: -0.0000

Data Index: 802491 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.1011. Min Act: -0.0000

Data Index: 173663 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.2087. Min Act: -0.0000

Data Index: 111885 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.0400. Min Act: -0.0000

Data Index: 506437 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.2256. Min Act: -0.0000

Data Index: 887192 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.0992. Min Act: -0.0000

Data Index: 505659 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.1083. Min Act: -0.0000

Data Index: 161402 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.0936. Min Act: -0.0000

Data Index: 96914 (C4 (Web Text))

Max Activating Token Index: 1003

Text #15

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1242538 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 2.9450. Min Range: -2.9450

Max Act: 1.9311. Min Act: -0.0000

Data Index: 482733 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.0372. Min Act: -0.0000

Data Index: 520724 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.9450. Min Range: -2.9450

Max Act: 2.0083. Min Act: -0.0000

Data Index: 504735 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 2.9450. Min Range: -2.9450

Max Act: 1.9031. Min Act: -0.0000

Data Index: 668551 (C4 (Web Text))

Max Activating Token Index: 967