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

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

Neuron 474 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: 1.5628. Min Range: -1.5628

Max Act: 1.5628. Min Act: -0.0002

Data Index: 1228653 (C4 (Web Text))

Max Activating Token Index: 387

Text #1

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5392. Min Act: -0.0002

Data Index: 1130149 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4998. Min Act: -0.0002

Data Index: 945466 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.5029. Min Act: -0.0002

Data Index: 216511 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4660. Min Act: -0.0002

Data Index: 1058871 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4979. Min Act: -0.0002

Data Index: 395976 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4811. Min Act: -0.0002

Data Index: 1211822 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4476. Min Act: -0.0002

Data Index: 760933 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4202. Min Act: -0.0002

Data Index: 1292035 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4233. Min Act: -0.0002

Data Index: 1290264 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4246. Min Act: -0.0002

Data Index: 993717 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4460. Min Act: -0.0002

Data Index: 240718 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4353. Min Act: -0.0002

Data Index: 754943 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3994. Min Act: -0.0002

Data Index: 448247 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4062. Min Act: -0.0002

Data Index: 545359 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4217. Min Act: -0.0002

Data Index: 619248 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3988. Min Act: -0.0002

Data Index: 230547 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.4034. Min Act: -0.0002

Data Index: 966868 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3903. Min Act: -0.0002

Data Index: 199182 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 1.5628. Min Range: -1.5628

Max Act: 1.3930. Min Act: -0.0002

Data Index: 195838 (C4 (Web Text))

Max Activating Token Index: 278