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

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

Neuron 3191 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8610. Min Range: -2.8610

Max Act: 2.8610. Min Act: -0.0000

Data Index: 126460 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 2.8610. Min Range: -2.8610

Max Act: 2.3568. Min Act: -0.0000

Data Index: 597495 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 2.8610. Min Range: -2.8610

Max Act: 2.1934. Min Act: -0.0000

Data Index: 1078090 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.7723. Min Act: -0.0000

Data Index: 149008 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 2.8610. Min Range: -2.8610

Max Act: 2.0044. Min Act: -0.0000

Data Index: 990515 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.9455. Min Act: -0.0000

Data Index: 906512 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.8591. Min Act: -0.0000

Data Index: 1117668 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.7199. Min Act: -0.0000

Data Index: 497943 (C4 (Web Text))

Max Activating Token Index: 646

Text #8

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.8276. Min Act: -0.0000

Data Index: 590575 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.8117. Min Act: -0.0000

Data Index: 312375 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1220513 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.5628. Min Act: -0.0000

Data Index: 836073 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.5845. Min Act: -0.0000

Data Index: 43820 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.6504. Min Act: -0.0000

Data Index: 891651 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.4312. Min Act: -0.0000

Data Index: 205430 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.4621. Min Act: -0.0000

Data Index: 327922 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1306006 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.4416. Min Act: -0.0000

Data Index: 475928 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.5301. Min Act: -0.0000

Data Index: 1189933 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 2.8610. Min Range: -2.8610

Max Act: 1.4247. Min Act: -0.0000

Data Index: 345503 (C4 (Web Text))

Max Activating Token Index: 695