Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3386 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0246. Min Act: -0.0001

Data Index: 652734 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1018759 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0232. Min Act: -0.0001

Data Index: 416639 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0228. Min Act: -0.0001

Data Index: 285666 (C4 (Web Text))

Max Activating Token Index: 407

Text #4

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1244240 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0223. Min Act: -0.0001

Data Index: 352819 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0228. Min Act: -0.0001

Data Index: 190429 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0222. Min Act: -0.0001

Data Index: 251776 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0215. Min Act: -0.0001

Data Index: 105445 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0001

Data Index: 1089148 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0214. Min Act: -0.0001

Data Index: 449750 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0219. Min Act: -0.0001

Data Index: 576333 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0214. Min Act: -0.0001

Data Index: 289790 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0213. Min Act: -0.0001

Data Index: 348331 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0213. Min Act: -0.0001

Data Index: 505124 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0208. Min Act: -0.0001

Data Index: 1159029 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0209. Min Act: -0.0001

Data Index: 586174 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0213. Min Act: -0.0001

Data Index: 267619 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0213. Min Act: -0.0001

Data Index: 378160 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.0246. Min Range: -0.0246

Max Act: 0.0209. Min Act: -0.0001

Data Index: 256151 (C4 (Web Text))

Max Activating Token Index: 575