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

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

Neuron 5674 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.3721. Min Act: -0.0001

Data Index: 754305 (C4 (Web Text))

Max Activating Token Index: 480

Text #1

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.2001. Min Act: -0.0001

Data Index: 974804 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9835. Min Act: -0.0001

Data Index: 959982 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0820. Min Act: -0.0001

Data Index: 1304689 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0593. Min Act: -0.0001

Data Index: 931927 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9766. Min Act: -0.0001

Data Index: 1264590 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0658. Min Act: -0.0001

Data Index: 1188744 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0359. Min Act: -0.0001

Data Index: 793050 (C4 (Web Text))

Max Activating Token Index: 144

Text #8

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9801. Min Act: -0.0001

Data Index: 1216956 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9815. Min Act: -0.0001

Data Index: 477523 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0233. Min Act: -0.0001

Data Index: 60720 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9324. Min Act: -0.0001

Data Index: 894279 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.7124. Min Act: -0.0001

Data Index: 950576 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9066. Min Act: -0.0000

Data Index: 43871 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 1.3721. Min Range: -1.3721

Max Act: 1.0963. Min Act: -0.0000

Data Index: 20316 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9507. Min Act: -0.0001

Data Index: 303727 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9176. Min Act: -0.0001

Data Index: 1180786 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9367. Min Act: -0.0000

Data Index: 320542 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.8640. Min Act: -0.0001

Data Index: 276989 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 1.3721. Min Range: -1.3721

Max Act: 0.9227. Min Act: -0.0001

Data Index: 1334877 (C4 (Web Text))

Max Activating Token Index: 669