Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3775 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.8082. Min Act: -0.0000

Data Index: 800117 (C4 (Web Text))

Max Activating Token Index: 599

Text #1

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.5027. Min Act: -0.0000

Data Index: 711525 (C4 (Web Text))

Max Activating Token Index: 590

Text #2

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.4484. Min Act: -0.0000

Data Index: 250618 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.5247. Min Act: -0.0000

Data Index: 1280314 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3942. Min Act: -0.0000

Data Index: 1292852 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2882. Min Act: -0.0000

Data Index: 576582 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3279. Min Act: -0.0000

Data Index: 812660 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.4097. Min Act: -0.0000

Data Index: 443825 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1004473 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2689. Min Act: -0.0000

Data Index: 760303 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2711. Min Act: -0.0000

Data Index: 623742 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2187. Min Act: -0.0000

Data Index: 60640 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.3082. Min Act: -0.0000

Data Index: 922217 (C4 (Web Text))

Max Activating Token Index: 1013

Text #13

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2289. Min Act: -0.0000

Data Index: 573937 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.4148. Min Act: -0.0000

Data Index: 873119 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1308825 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1489. Min Act: -0.0000

Data Index: 845568 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1175915 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1203. Min Act: -0.0000

Data Index: 1138170 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.8082. Min Range: -1.8082

Max Act: 1.1754. Min Act: -0.0000

Data Index: 153137 (C4 (Web Text))

Max Activating Token Index: 715