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

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

Neuron 2079 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.1152. Min Act: -0.0000

Data Index: 534964 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 3.1542. Min Range: -3.1542

Max Act: 3.1542. Min Act: -0.0000

Data Index: 232839 (C4 (Web Text))

Max Activating Token Index: 66

Text #2

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.9934. Min Act: -0.0000

Data Index: 554431 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.7827. Min Act: -0.0000

Data Index: 693974 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.7671. Min Act: -0.0000

Data Index: 1318284 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.7652. Min Act: -0.0000

Data Index: 274951 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.7597. Min Act: -0.0000

Data Index: 860746 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.6872. Min Act: -0.0000

Data Index: 1183635 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.6913. Min Act: -0.0000

Data Index: 1159724 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.5922. Min Act: -0.0000

Data Index: 966110 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.6862. Min Act: -0.0000

Data Index: 1156041 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.3091. Min Act: 0.0000

Data Index: 422666 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.4093. Min Act: -0.0000

Data Index: 395596 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.5378. Min Act: -0.0000

Data Index: 767245 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.5096. Min Act: -0.0000

Data Index: 232127 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1045570 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.4559. Min Act: -0.0000

Data Index: 969324 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.3443. Min Act: 0.0000

Data Index: 711197 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.3238. Min Act: -0.0000

Data Index: 1026852 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.1542. Min Range: -3.1542

Max Act: 2.5809. Min Act: -0.0000

Data Index: 1281709 (C4 (Web Text))

Max Activating Token Index: 408