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

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

Neuron 4694 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1912. Min Act: -0.0000

Data Index: 459538 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1834. Min Act: -0.0000

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.3006. Min Act: -0.0000

Data Index: 272773 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1761. Min Act: -0.0000

Data Index: 1320238 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1691. Min Act: -0.0000

Data Index: 763214 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1690. Min Act: -0.0000

Data Index: 345463 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.3115. Min Act: -0.0000

Data Index: 913625 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1832. Min Act: -0.0000

Data Index: 41115 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0636. Min Act: -0.0000

Data Index: 754827 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0702. Min Act: -0.0000

Data Index: 710989 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0511. Min Act: -0.0000

Data Index: 742027 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0487. Min Act: -0.0000

Data Index: 894071 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0259. Min Act: -0.0000

Data Index: 1161395 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0214. Min Act: -0.0000

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0374. Min Act: -0.0000

Data Index: 705197 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.1691. Min Act: -0.0000

Data Index: 1159734 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 3.3115. Min Range: -3.3115

Max Act: 2.8936. Min Act: -0.0000

Data Index: 1086034 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 3.3115. Min Range: -3.3115

Max Act: 3.0010. Min Act: -0.0000

Data Index: 749035 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 3.3115. Min Range: -3.3115

Max Act: 2.9980. Min Act: -0.0000

Data Index: 590404 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.3115. Min Range: -3.3115

Max Act: 2.8439. Min Act: -0.0000

Data Index: 470431 (C4 (Web Text))

Max Activating Token Index: 66