Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1450275 (Python Code)

Max Activating Token Index: 1012

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0196. Min Act: -0.0003

Data Index: 69907 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0003

Data Index: 190464 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1511774 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1114993 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0161. Min Act: -0.0003

Data Index: 991243 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1515643 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1543195 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0156. Min Act: -0.0003

Data Index: 182834 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1476851 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1462795 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0146. Min Act: -0.0003

Data Index: 1536352 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0003

Data Index: 312377 (C4 (Web Text))

Max Activating Token Index: 601

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1444044 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0161. Min Act: -0.0003

Data Index: 1430238 (Python Code)

Max Activating Token Index: 942

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0151. Min Act: -0.0003

Data Index: 847242 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1485316 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1296959 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0144. Min Act: -0.0003

Data Index: 1148347 (C4 (Web Text))

Max Activating Token Index: 969

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1070731 (C4 (Web Text))

Max Activating Token Index: 87