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

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

Neuron 1704 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0179. Min Act: -0.0003

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1254612 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1030419 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0165. Min Act: -0.0003

Data Index: 206299 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0152. Min Act: -0.0003

Data Index: 854240 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0171. Min Act: -0.0002

Data Index: 750154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0150. Min Act: -0.0003

Data Index: 871036 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0145. Min Act: -0.0003

Data Index: 1306940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0148. Min Act: -0.0003

Data Index: 809877 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0146. Min Act: -0.0002

Data Index: 212980 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0141. Min Act: -0.0003

Data Index: 483722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0139. Min Act: -0.0003

Data Index: 375558 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0141. Min Act: -0.0002

Data Index: 924678 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0135. Min Act: -0.0002

Data Index: 1324479 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0128. Min Act: -0.0002

Data Index: 903848 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0135. Min Act: -0.0003

Data Index: 1470501 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0134. Min Act: -0.0002

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0179. Min Range: -0.0179

Max Act: 0.0126. Min Act: -0.0002

Data Index: 1008221 (C4 (Web Text))

Max Activating Token Index: 1023