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

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

Neuron 5908 in Layer 1

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: 1.6767. Min Range: -1.6767

Max Act: 1.6371. Min Act: -0.0002

Data Index: 1327078 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6119. Min Act: -0.0002

Data Index: 471735 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.6767. Min Act: -0.0002

Data Index: 584884 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5931. Min Act: -0.0002

Data Index: 650673 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5632. Min Act: -0.0002

Data Index: 980277 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5299. Min Act: -0.0002

Data Index: 1246527 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5524. Min Act: -0.0002

Data Index: 1276385 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5118. Min Act: -0.0002

Data Index: 1306800 (C4 (Web Text))

Max Activating Token Index: 408

Text #8

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4948. Min Act: -0.0002

Data Index: 682242 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5263. Min Act: -0.0002

Data Index: 588806 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5320. Min Act: -0.0002

Data Index: 803530 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4801. Min Act: -0.0002

Data Index: 274261 (C4 (Web Text))

Max Activating Token Index: 489

Text #12

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5170. Min Act: -0.0002

Data Index: 610493 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4676. Min Act: -0.0002

Data Index: 1259476 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5092. Min Act: -0.0002

Data Index: 200227 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4723. Min Act: -0.0002

Data Index: 928069 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.5025. Min Act: -0.0002

Data Index: 928583 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4688. Min Act: -0.0002

Data Index: 144214 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4312. Min Act: -0.0002

Data Index: 1035774 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.6767. Min Range: -1.6767

Max Act: 1.4644. Min Act: -0.0002

Data Index: 856173 (C4 (Web Text))

Max Activating Token Index: 16