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

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

Neuron 3250 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0190. Min Act: -0.0001

Data Index: 1629172 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0213. Min Act: -0.0001

Data Index: 1431725 (Python Code)

Max Activating Token Index: 823

Text #2

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0174. Min Act: -0.0001

Data Index: 384878 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0185. Min Act: -0.0001

Data Index: 1589422 (Python Code)

Max Activating Token Index: 777

Text #4

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0168. Min Act: -0.0001

Data Index: 1402276 (Python Code)

Max Activating Token Index: 998

Text #5

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0173. Min Act: -0.0001

Data Index: 1560188 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0167. Min Act: -0.0000

Data Index: 1653519 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1555023 (Python Code)

Max Activating Token Index: 960

Text #8

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1599979 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0159. Min Act: -0.0001

Data Index: 815982 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0143. Min Act: -0.0001

Data Index: 1615864 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0155. Min Act: -0.0001

Data Index: 164579 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0146. Min Act: -0.0000

Data Index: 1479603 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0145. Min Act: -0.0001

Data Index: 1654567 (Python Code)

Max Activating Token Index: 994

Text #14

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0140. Min Act: -0.0000

Data Index: 1619421 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0136. Min Act: -0.0001

Data Index: 1423795 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0137. Min Act: -0.0001

Data Index: 1413769 (Python Code)

Max Activating Token Index: 976

Text #17

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0135. Min Act: -0.0000

Data Index: 1643007 (Python Code)

Max Activating Token Index: 964

Text #18

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0140. Min Act: -0.0001

Data Index: 1378226 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 0.0213. Min Range: -0.0213

Max Act: 0.0147. Min Act: -0.0001

Data Index: 537173 (C4 (Web Text))

Max Activating Token Index: 1017