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

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

Neuron 1017 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: 1.3091. Min Range: -1.3091

Max Act: 1.3091. Min Act: -0.0003

Data Index: 1158649 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.2363. Min Act: -0.0002

Data Index: 1255912 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.2508. Min Act: -0.0003

Data Index: 767515 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.2273. Min Act: -0.0002

Data Index: 340511 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1457. Min Act: -0.0003

Data Index: 1319990 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1550. Min Act: -0.0003

Data Index: 266250 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1419. Min Act: -0.0002

Data Index: 582235 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1383. Min Act: -0.0002

Data Index: 343784 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1186. Min Act: -0.0003

Data Index: 1162023 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1183. Min Act: -0.0003

Data Index: 1342096 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1363. Min Act: -0.0002

Data Index: 881378 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1251. Min Act: -0.0002

Data Index: 188346 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0894. Min Act: -0.0002

Data Index: 14165 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.1063. Min Act: -0.0002

Data Index: 911712 (C4 (Web Text))

Max Activating Token Index: 272

Text #14

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0932. Min Act: -0.0002

Data Index: 86368 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0767. Min Act: -0.0002

Data Index: 77637 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0787. Min Act: -0.0002

Data Index: 479370 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0668. Min Act: -0.0003

Data Index: 502873 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0633. Min Act: -0.0002

Data Index: 905859 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.3091. Min Range: -1.3091

Max Act: 1.0732. Min Act: -0.0002

Data Index: 206504 (C4 (Web Text))

Max Activating Token Index: 464