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

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

Neuron 1184 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: 2.6454. Min Range: -2.6454

Max Act: 2.6454. Min Act: -0.0002

Data Index: 468238 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.3060. Min Act: -0.0002

Data Index: 982360 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.1565. Min Act: -0.0002

Data Index: 1191238 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.0548. Min Act: -0.0002

Data Index: 572540 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 2.6454. Min Range: -2.6454

Max Act: 2.0554. Min Act: -0.0002

Data Index: 646864 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.9521. Min Act: -0.0002

Data Index: 787497 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.9760. Min Act: -0.0002

Data Index: 1025342 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.9451. Min Act: -0.0002

Data Index: 1104398 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7974. Min Act: -0.0002

Data Index: 964353 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.8112. Min Act: -0.0002

Data Index: 735177 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.8064. Min Act: -0.0002

Data Index: 509284 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.8001. Min Act: -0.0002

Data Index: 1007338 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7513. Min Act: -0.0002

Data Index: 112528 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7436. Min Act: -0.0002

Data Index: 1155824 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7855. Min Act: -0.0002

Data Index: 301550 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7447. Min Act: -0.0002

Data Index: 740905 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7533. Min Act: -0.0002

Data Index: 836228 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7248. Min Act: -0.0002

Data Index: 36268 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7534. Min Act: -0.0002

Data Index: 973658 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 2.6454. Min Range: -2.6454

Max Act: 1.7324. Min Act: -0.0002

Data Index: 455696 (C4 (Web Text))

Max Activating Token Index: 93