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

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

Neuron 3500 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0001

Data Index: 426208 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0154. Min Act: -0.0000

Data Index: 1241453 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0158. Min Act: -0.0001

Data Index: 693668 (C4 (Web Text))

Max Activating Token Index: 54

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0155. Min Act: -0.0001

Data Index: 570064 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0148. Min Act: -0.0000

Data Index: 1507837 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0152. Min Act: -0.0001

Data Index: 96554 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0152. Min Act: -0.0000

Data Index: 1546821 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0146. Min Act: -0.0000

Data Index: 1121897 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0147. Min Act: -0.0001

Data Index: 193647 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0146. Min Act: -0.0001

Data Index: 1038878 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0144. Min Act: -0.0001

Data Index: 934042 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0143. Min Act: -0.0000

Data Index: 1541887 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0143. Min Act: -0.0001

Data Index: 447235 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1419713 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1560091 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0138. Min Act: -0.0000

Data Index: 1424545 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1367226 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1628460 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0134. Min Act: -0.0000

Data Index: 435290 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0139. Min Act: -0.0000

Data Index: 1622522 (Python Code)

Max Activating Token Index: 68