Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 464 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0180. Min Act: -0.0006

Data Index: 392115 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0176. Min Act: -0.0005

Data Index: 499719 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0164. Min Act: -0.0006

Data Index: 1305116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0157. Min Act: -0.0006

Data Index: 970683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0156. Min Act: -0.0006

Data Index: 47672 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0158. Min Act: -0.0006

Data Index: 1374573 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0154. Min Act: -0.0006

Data Index: 1113049 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0153. Min Act: -0.0006

Data Index: 803181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0153. Min Act: -0.0006

Data Index: 540834 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0152. Min Act: -0.0006

Data Index: 1010098 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0152. Min Act: -0.0005

Data Index: 468002 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0152. Min Act: -0.0006

Data Index: 176792 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0152. Min Act: -0.0006

Data Index: 280718 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1395317 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0148. Min Act: -0.0005

Data Index: 1421602 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0147. Min Act: -0.0006

Data Index: 785249 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0146. Min Act: -0.0006

Data Index: 1092970 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0145. Min Act: -0.0005

Data Index: 1645443 (Python Code)

Max Activating Token Index: 829

Text #18

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1419724 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.0180. Min Range: -0.0180

Max Act: 0.0142. Min Act: -0.0005

Data Index: 1567725 (Python Code)

Max Activating Token Index: 740