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

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

Neuron 185 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: 0.9313. Min Range: -0.9313

Max Act: 0.9313. Min Act: -0.0002

Data Index: 843095 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8936. Min Act: -0.0002

Data Index: 33247 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8295. Min Act: -0.0002

Data Index: 1210174 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8324. Min Act: -0.0002

Data Index: 395278 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.8036. Min Act: -0.0002

Data Index: 1005269 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7740. Min Act: -0.0002

Data Index: 484303 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7935. Min Act: -0.0002

Data Index: 793509 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7845. Min Act: -0.0002

Data Index: 237519 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7696. Min Act: -0.0002

Data Index: 883769 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7512. Min Act: -0.0002

Data Index: 371615 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7464. Min Act: -0.0002

Data Index: 1157688 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7445. Min Act: -0.0002

Data Index: 1159617 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7399. Min Act: -0.0002

Data Index: 288727 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7428. Min Act: -0.0002

Data Index: 1070314 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7530. Min Act: -0.0002

Data Index: 911020 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7338. Min Act: -0.0003

Data Index: 1078050 (C4 (Web Text))

Max Activating Token Index: 29

Text #16

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7377. Min Act: -0.0002

Data Index: 214488 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7160. Min Act: -0.0002

Data Index: 470265 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7293. Min Act: -0.0002

Data Index: 121387 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.9313. Min Range: -0.9313

Max Act: 0.7129. Min Act: -0.0002

Data Index: 1118022 (C4 (Web Text))

Max Activating Token Index: 791