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

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

Neuron 2163 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3006. Min Act: -0.0000

Data Index: 223428 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1899. Min Act: -0.0000

Data Index: 667064 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1088034 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2539. Min Act: -0.0001

Data Index: 58704 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2598. Min Act: -0.0001

Data Index: 45206 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1013473 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 301532 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2548. Min Act: -0.0000

Data Index: 1196259 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2122. Min Act: -0.0000

Data Index: 26339 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2268. Min Act: -0.0001

Data Index: 879351 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2244. Min Act: -0.0000

Data Index: 175677 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2154. Min Act: -0.0001

Data Index: 527056 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1929. Min Act: -0.0001

Data Index: 591798 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1998. Min Act: -0.0001

Data Index: 1247080 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2221. Min Act: -0.0001

Data Index: 1299033 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2041. Min Act: -0.0000

Data Index: 904063 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2159. Min Act: -0.0001

Data Index: 1043784 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1937. Min Act: -0.0001

Data Index: 1252504 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1940. Min Act: -0.0001

Data Index: 246192 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1923. Min Act: -0.0001

Data Index: 860667 (C4 (Web Text))

Max Activating Token Index: 970