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

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

Neuron 2055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4460. Min Range: -3.4460

Max Act: 3.4460. Min Act: -0.0001

Data Index: 622473 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.9721. Min Act: -0.0001

Data Index: 1145075 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.9484. Min Act: -0.0001

Data Index: 492130 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.8485. Min Act: -0.0001

Data Index: 558153 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.9814. Min Act: -0.0001

Data Index: 1214296 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.6805. Min Act: -0.0001

Data Index: 759677 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.5402. Min Act: -0.0001

Data Index: 1279550 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.9159. Min Act: -0.0001

Data Index: 226160 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.5130. Min Act: -0.0001

Data Index: 656728 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.5037. Min Act: -0.0001

Data Index: 1043476 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.7515. Min Act: -0.0001

Data Index: 127052 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.5867. Min Act: -0.0001

Data Index: 308326 (C4 (Web Text))

Max Activating Token Index: 150

Text #12

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.6569. Min Act: -0.0001

Data Index: 169616 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.7840. Min Act: -0.0001

Data Index: 227978 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.6459. Min Act: -0.0001

Data Index: 580760 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.3755. Min Act: -0.0001

Data Index: 309583 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.6113. Min Act: -0.0001

Data Index: 1067042 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.5466. Min Act: -0.0001

Data Index: 374906 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.4179. Min Act: -0.0001

Data Index: 1064751 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 3.4460. Min Range: -3.4460

Max Act: 2.6298. Min Act: -0.0001

Data Index: 1244691 (C4 (Web Text))

Max Activating Token Index: 978