Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 827 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.3213. Min Act: -0.0001

Data Index: 660372 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2440. Min Act: -0.0000

Data Index: 550103 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2429. Min Act: -0.0001

Data Index: 874490 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2391. Min Act: -0.0001

Data Index: 528898 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2266. Min Act: -0.0000

Data Index: 242413 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2195. Min Act: -0.0000

Data Index: 144950 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2146. Min Act: -0.0001

Data Index: 1178381 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2149. Min Act: -0.0000

Data Index: 1023897 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2426. Min Act: -0.0001

Data Index: 652331 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2206. Min Act: -0.0001

Data Index: 257393 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2201. Min Act: -0.0001

Data Index: 558198 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2154. Min Act: -0.0001

Data Index: 742912 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1078407 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2250. Min Act: -0.0000

Data Index: 780589 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2140. Min Act: -0.0001

Data Index: 1038151 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2060. Min Act: -0.0000

Data Index: 711988 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2249. Min Act: -0.0000

Data Index: 1066948 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2078. Min Act: -0.0000

Data Index: 54229 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.2093. Min Act: -0.0001

Data Index: 617414 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.3213. Min Range: -0.3213

Max Act: 0.1929. Min Act: 0.0000

Data Index: 234382 (C4 (Web Text))

Max Activating Token Index: 344