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

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

Neuron 1703 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.8348. Min Act: -0.0000

Data Index: 644088 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.5482. Min Act: -0.0000

Data Index: 437130 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.8348. Min Range: -1.8348

Max Act: 1.1276. Min Act: -0.0001

Data Index: 810692 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.9987. Min Act: -0.0000

Data Index: 977181 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.9488. Min Act: -0.0001

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8778. Min Act: -0.0000

Data Index: 600538 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8127. Min Act: -0.0000

Data Index: 1269084 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.7581. Min Act: -0.0000

Data Index: 89288 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8652. Min Act: -0.0001

Data Index: 276984 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8595. Min Act: -0.0000

Data Index: 990503 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1037667 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8256. Min Act: -0.0000

Data Index: 932101 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1291914 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1165448 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1027744 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8657. Min Act: -0.0000

Data Index: 873873 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8794. Min Act: -0.0000

Data Index: 580487 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.8148. Min Act: -0.0000

Data Index: 544744 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.7708. Min Act: -0.0001

Data Index: 445871 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 1.8348. Min Range: -1.8348

Max Act: 0.7665. Min Act: -0.0001

Data Index: 1341151 (C4 (Web Text))

Max Activating Token Index: 429