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

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

Neuron 4036 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0190. Min Act: -0.0003

Data Index: 687937 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0151. Min Act: -0.0003

Data Index: 596051 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0141. Min Act: -0.0003

Data Index: 825958 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0147. Min Act: -0.0003

Data Index: 794231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0147. Min Act: -0.0003

Data Index: 1107262 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0115. Min Act: -0.0003

Data Index: 918176 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0129. Min Act: -0.0003

Data Index: 648972 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0125. Min Act: -0.0003

Data Index: 537115 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0150. Min Act: -0.0003

Data Index: 189922 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0123. Min Act: -0.0004

Data Index: 1286745 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0136. Min Act: -0.0003

Data Index: 1276692 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0121. Min Act: -0.0003

Data Index: 1228983 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0126. Min Act: -0.0003

Data Index: 586248 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0129. Min Act: -0.0003

Data Index: 99433 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1242432 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0119. Min Act: -0.0003

Data Index: 14469 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0114. Min Act: -0.0003

Data Index: 897850 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0125. Min Act: -0.0003

Data Index: 1072842 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0163. Min Act: -0.0003

Data Index: 826821 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0190. Min Range: -0.0190

Max Act: 0.0134. Min Act: -0.0003

Data Index: 165463 (C4 (Web Text))

Max Activating Token Index: 598