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

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

Neuron 2235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.3549. Min Act: -0.0000

Data Index: 1339674 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.3288. Min Act: -0.0000

Data Index: 278209 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.1341. Min Act: -0.0000

Data Index: 657877 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.3212. Min Act: -0.0000

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.1420. Min Act: -0.0000

Data Index: 639627 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.3529. Min Act: -0.0000

Data Index: 342228 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.3646. Min Act: -0.0000

Data Index: 1189824 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.1688. Min Act: -0.0000

Data Index: 637672 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.1200. Min Act: -0.0000

Data Index: 420589 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 6.3646. Min Range: -6.3646

Max Act: 6.1231. Min Act: -0.0000

Data Index: 72559 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9904. Min Act: -0.0000

Data Index: 958162 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9806. Min Act: -0.0000

Data Index: 149824 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9742. Min Act: -0.0000

Data Index: 1066257 (C4 (Web Text))

Max Activating Token Index: 519

Text #13

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.5962. Min Act: -0.0000

Data Index: 568646 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9736. Min Act: -0.0000

Data Index: 562913 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9690. Min Act: -0.0000

Data Index: 209366 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9014. Min Act: -0.0000

Data Index: 58214 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.9222. Min Act: -0.0000

Data Index: 1341192 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.6702. Min Act: -0.0000

Data Index: 405379 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 6.3646. Min Range: -6.3646

Max Act: 5.8143. Min Act: -0.0000

Data Index: 464935 (C4 (Web Text))

Max Activating Token Index: 50