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

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

Neuron 4664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2469. Min Range: -3.2469

Max Act: 3.2469. Min Act: -0.0000

Data Index: 885594 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.8810. Min Act: -0.0000

Data Index: 718095 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.6190. Min Act: -0.0000

Data Index: 1232576 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5257. Min Act: -0.0000

Data Index: 301416 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.4726. Min Act: -0.0000

Data Index: 873587 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.5659. Min Act: -0.0000

Data Index: 964590 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.2686. Min Act: -0.0000

Data Index: 68638 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 3.2469. Min Range: -3.2469

Max Act: 1.7041. Min Act: -0.0000

Data Index: 812703 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1004525 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.4248. Min Act: -0.0000

Data Index: 1010812 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.3945. Min Act: -0.0000

Data Index: 923404 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.3348. Min Act: -0.0000

Data Index: 498972 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.3935. Min Act: 0.0000

Data Index: 655956 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.4739. Min Act: -0.0000

Data Index: 1232797 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.4529. Min Act: -0.0000

Data Index: 16472 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.3187. Min Act: -0.0000

Data Index: 389347 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.0283. Min Act: -0.0000

Data Index: 833466 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 3.2469. Min Range: -3.2469

Max Act: 1.7963. Min Act: -0.0000

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.0131. Min Act: -0.0000

Data Index: 137628 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 3.2469. Min Range: -3.2469

Max Act: 2.1173. Min Act: -0.0000

Data Index: 828025 (C4 (Web Text))

Max Activating Token Index: 205