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

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

Neuron 1978 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.8839. Min Act: -0.0000

Data Index: 1217823 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.9107. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.8040. Min Act: 0.0000

Data Index: 1220806 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.6526. Min Act: 0.0000

Data Index: 1323360 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.5871. Min Act: -0.0000

Data Index: 1329089 (C4 (Web Text))

Max Activating Token Index: 222

Text #5

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.4950. Min Act: -0.0000

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.4417. Min Act: -0.0000

Data Index: 235576 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.4879. Min Act: -0.0000

Data Index: 957471 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.4412. Min Act: -0.0000

Data Index: 304862 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.3542. Min Act: -0.0000

Data Index: 1141385 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.2903. Min Act: -0.0000

Data Index: 648857 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.2375. Min Act: -0.0000

Data Index: 881816 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.2356. Min Act: 0.0000

Data Index: 443795 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.2111. Min Act: -0.0000

Data Index: 486101 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.0795. Min Act: -0.0000

Data Index: 995042 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.1700. Min Act: -0.0000

Data Index: 817216 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.1701. Min Act: -0.0000

Data Index: 1172036 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.1524. Min Act: 0.0000

Data Index: 150087 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.1861. Min Act: -0.0000

Data Index: 1321435 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.9107. Min Range: -1.9107

Max Act: 1.1180. Min Act: -0.0000

Data Index: 481821 (C4 (Web Text))

Max Activating Token Index: 731