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

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

Neuron 1276 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: 6.2099. Min Range: -6.2099

Max Act: 6.2099. Min Act: -0.0000

Data Index: 397055 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 6.2099. Min Range: -6.2099

Max Act: 6.0701. Min Act: -0.0000

Data Index: 383849 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.3661. Min Act: -0.0000

Data Index: 308089 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.9168. Min Act: -0.0000

Data Index: 629319 (C4 (Web Text))

Max Activating Token Index: 54

Text #4

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.5406. Min Act: -0.0000

Data Index: 658179 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.5287. Min Act: -0.0000

Data Index: 539058 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.2514. Min Act: -0.0000

Data Index: 1146825 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.9391. Min Act: -0.0000

Data Index: 536346 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.9153. Min Act: -0.0000

Data Index: 1033133 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.4352. Min Act: -0.0000

Data Index: 341545 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.7990. Min Act: -0.0000

Data Index: 999520 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.1173. Min Act: -0.0000

Data Index: 739233 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.9564. Min Act: -0.0000

Data Index: 706980 (C4 (Web Text))

Max Activating Token Index: 782

Text #13

Max Range: 6.2099. Min Range: -6.2099

Max Act: 5.4174. Min Act: -0.0000

Data Index: 970259 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.5358. Min Act: -0.0000

Data Index: 1207900 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.7046. Min Act: -0.0000

Data Index: 897835 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.6331. Min Act: -0.0000

Data Index: 34160 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.9870. Min Act: -0.0000

Data Index: 468065 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.9009. Min Act: -0.0000

Data Index: 1033280 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 6.2099. Min Range: -6.2099

Max Act: 4.8539. Min Act: -0.0000

Data Index: 820213 (C4 (Web Text))

Max Activating Token Index: 20