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

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

Neuron 3366 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7930. Min Act: -0.0001

Data Index: 330014 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1049445 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1488796 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1474731 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7350. Min Act: -0.0002

Data Index: 224849 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6966. Min Act: -0.0002

Data Index: 634677 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7554. Min Act: -0.0001

Data Index: 1348173 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7143. Min Act: -0.0001

Data Index: 704605 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7464. Min Act: -0.0001

Data Index: 67248 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7274. Min Act: -0.0001

Data Index: 1288285 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7153. Min Act: -0.0001

Data Index: 1106959 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7196. Min Act: -0.0001

Data Index: 1468364 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6968. Min Act: -0.0001

Data Index: 1326875 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7154. Min Act: -0.0001

Data Index: 195143 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7084. Min Act: -0.0001

Data Index: 638001 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6916. Min Act: -0.0001

Data Index: 557457 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7112. Min Act: -0.0001

Data Index: 451429 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6469. Min Act: -0.0001

Data Index: 710204 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.7179. Min Act: -0.0001

Data Index: 547982 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.7930. Min Range: -0.7930

Max Act: 0.6576. Min Act: -0.0001

Data Index: 697279 (C4 (Web Text))

Max Activating Token Index: 25