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

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

Neuron 2309 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: 2.5961. Min Range: -2.5961

Max Act: 2.5961. Min Act: -0.0001

Data Index: 1021460 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.5134. Min Act: -0.0001

Data Index: 1157206 (C4 (Web Text))

Max Activating Token Index: 336

Text #2

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.4537. Min Act: -0.0001

Data Index: 1208188 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.3809. Min Act: -0.0001

Data Index: 998564 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.4087. Min Act: -0.0001

Data Index: 584832 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.3243. Min Act: -0.0001

Data Index: 954416 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.2947. Min Act: -0.0001

Data Index: 650542 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.2186. Min Act: -0.0001

Data Index: 438121 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.1087. Min Act: -0.0001

Data Index: 603592 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.1288. Min Act: -0.0001

Data Index: 1186554 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.1538. Min Act: -0.0001

Data Index: 628344 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.1267. Min Act: -0.0001

Data Index: 1210827 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0723. Min Act: -0.0001

Data Index: 1087109 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0178. Min Act: -0.0001

Data Index: 906850 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0213. Min Act: -0.0001

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0965. Min Act: -0.0001

Data Index: 433498 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0262. Min Act: -0.0001

Data Index: 285476 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0127. Min Act: -0.0001

Data Index: 372177 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 2.5961. Min Range: -2.5961

Max Act: 2.0459. Min Act: -0.0001

Data Index: 961710 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 2.5961. Min Range: -2.5961

Max Act: 1.9726. Min Act: -0.0001

Data Index: 598052 (C4 (Web Text))

Max Activating Token Index: 654