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

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

Neuron 1268 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5263. Min Act: -0.0000

Data Index: 246999 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.5033. Min Act: -0.0000

Data Index: 971501 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4955. Min Act: -0.0000

Data Index: 491919 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1246464 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4492. Min Act: -0.0000

Data Index: 329935 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4641. Min Act: -0.0000

Data Index: 659112 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4333. Min Act: -0.0000

Data Index: 199668 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4241. Min Act: -0.0000

Data Index: 118621 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4247. Min Act: 0.0001

Data Index: 130273 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4177. Min Act: -0.0000

Data Index: 1267021 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.4020. Min Act: -0.0000

Data Index: 234520 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3886. Min Act: 0.0000

Data Index: 1076596 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3803. Min Act: -0.0000

Data Index: 82883 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3936. Min Act: -0.0000

Data Index: 458436 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3671. Min Act: -0.0000

Data Index: 1212103 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3865. Min Act: -0.0000

Data Index: 38715 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3901. Min Act: 0.0000

Data Index: 189416 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3688. Min Act: -0.0000

Data Index: 131394 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3843. Min Act: -0.0000

Data Index: 903497 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.5263. Min Range: -0.5263

Max Act: 0.3577. Min Act: -0.0000

Data Index: 874282 (C4 (Web Text))

Max Activating Token Index: 757