Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3802 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1249165 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1137797 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.1405. Min Act: -0.0000

Data Index: 1546840 (Python Code)

Max Activating Token Index: 73

Text #3

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.2069. Min Act: -0.0000

Data Index: 500706 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.1563. Min Act: -0.0000

Data Index: 795145 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0119. Min Act: -0.0000

Data Index: 211689 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.1651. Min Act: -0.0000

Data Index: 376321 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0497. Min Act: -0.0000

Data Index: 1130948 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0540. Min Act: -0.0000

Data Index: 893771 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0328. Min Act: -0.0000

Data Index: 1329915 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.1238. Min Act: -0.0000

Data Index: 493918 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0438. Min Act: -0.0000

Data Index: 187657 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.2404. Min Range: -1.2404

Max Act: 0.9577. Min Act: -0.0000

Data Index: 775184 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0522. Min Act: -0.0000

Data Index: 557292 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1031021 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.2404. Min Range: -1.2404

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1027951 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 1.2404. Min Range: -1.2404

Max Act: 1.0489. Min Act: -0.0000

Data Index: 1472596 (Python Code)

Max Activating Token Index: 434

Text #17

Max Range: 1.2404. Min Range: -1.2404

Max Act: 0.9748. Min Act: -0.0001

Data Index: 54794 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 1.2404. Min Range: -1.2404

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1463670 (Python Code)

Max Activating Token Index: 386

Text #19

Max Range: 1.2404. Min Range: -1.2404

Max Act: 0.9527. Min Act: -0.0000

Data Index: 944805 (C4 (Web Text))

Max Activating Token Index: 267