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

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

Neuron 198 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0175. Min Range: -2.0175

Max Act: 2.0175. Min Act: -0.0000

Data Index: 1103402 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.8434. Min Act: -0.0000

Data Index: 211249 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.5833. Min Act: -0.0000

Data Index: 676227 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.6509. Min Act: -0.0000

Data Index: 231598 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.6213. Min Act: 0.0000

Data Index: 1085371 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.4987. Min Act: 0.0001

Data Index: 1103422 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.4092. Min Act: 0.0000

Data Index: 277316 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1029560 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.3733. Min Act: -0.0000

Data Index: 4029 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.3612. Min Act: 0.0000

Data Index: 1186981 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.3571. Min Act: 0.0001

Data Index: 918099 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1202574 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.3360. Min Act: 0.0001

Data Index: 418947 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.3172. Min Act: -0.0000

Data Index: 71583 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2994. Min Act: 0.0000

Data Index: 854995 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1322277 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2906. Min Act: -0.0000

Data Index: 1067679 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2854. Min Act: -0.0000

Data Index: 62147 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2564. Min Act: 0.0000

Data Index: 329767 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 2.0175. Min Range: -2.0175

Max Act: 1.2533. Min Act: -0.0000

Data Index: 708817 (C4 (Web Text))

Max Activating Token Index: 44