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

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

Neuron 4647 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.6761. Min Act: -0.0000

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.5939. Min Act: -0.0000

Data Index: 284918 (C4 (Web Text))

Max Activating Token Index: 884

Text #2

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.9221. Min Act: -0.0000

Data Index: 1071597 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 2.6761. Min Range: -2.6761

Max Act: 2.0849. Min Act: -0.0000

Data Index: 352940 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.7921. Min Act: 0.0000

Data Index: 1079355 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.7526. Min Act: -0.0000

Data Index: 687537 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.7107. Min Act: -0.0000

Data Index: 271665 (C4 (Web Text))

Max Activating Token Index: 997

Text #7

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.6123. Min Act: -0.0000

Data Index: 983957 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.6294. Min Act: -0.0000

Data Index: 1166453 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.6066. Min Act: -0.0000

Data Index: 1232169 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.6053. Min Act: -0.0000

Data Index: 844131 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.6898. Min Act: -0.0000

Data Index: 587357 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.4356. Min Act: -0.0000

Data Index: 433205 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.4797. Min Act: -0.0000

Data Index: 108151 (C4 (Web Text))

Max Activating Token Index: 942

Text #14

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.4383. Min Act: -0.0000

Data Index: 147934 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.5237. Min Act: -0.0000

Data Index: 423633 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.4241. Min Act: -0.0000

Data Index: 667665 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.4016. Min Act: 0.0000

Data Index: 1080926 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.3951. Min Act: -0.0000

Data Index: 275644 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.6761. Min Range: -2.6761

Max Act: 1.3829. Min Act: -0.0000

Data Index: 318198 (C4 (Web Text))

Max Activating Token Index: 934