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

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

Neuron 3178 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.5000. Min Act: -0.0001

Data Index: 1338231 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.4261. Min Act: -0.0000

Data Index: 305902 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3766. Min Act: -0.0000

Data Index: 699192 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3989. Min Act: -0.0001

Data Index: 991060 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1157693 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3363. Min Act: -0.0000

Data Index: 1068470 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3175. Min Act: -0.0001

Data Index: 379439 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1250252 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2990. Min Act: -0.0001

Data Index: 174659 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2604. Min Act: -0.0000

Data Index: 72246 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2597. Min Act: -0.0001

Data Index: 30800 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2296. Min Act: -0.0001

Data Index: 871152 (C4 (Web Text))

Max Activating Token Index: 652

Text #12

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2450. Min Act: -0.0000

Data Index: 983855 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2451. Min Act: -0.0001

Data Index: 165288 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2336. Min Act: -0.0000

Data Index: 734027 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2420. Min Act: -0.0000

Data Index: 1100237 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2087. Min Act: -0.0000

Data Index: 501716 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2369. Min Act: -0.0001

Data Index: 1272642 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2126. Min Act: -0.0000

Data Index: 521093 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.5000. Min Range: -0.5000

Max Act: 0.2114. Min Act: -0.0001

Data Index: 793592 (C4 (Web Text))

Max Activating Token Index: 897