Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7986. Min Act: -0.0001

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.7192. Min Act: -0.0001

Data Index: 95051 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6756. Min Act: -0.0001

Data Index: 1214534 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6784. Min Act: -0.0001

Data Index: 896069 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6826. Min Act: -0.0001

Data Index: 333135 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6400. Min Act: -0.0001

Data Index: 309447 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.6261. Min Act: -0.0001

Data Index: 1164225 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5974. Min Act: -0.0001

Data Index: 836219 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5925. Min Act: -0.0001

Data Index: 345286 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5722. Min Act: -0.0001

Data Index: 246422 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5876. Min Act: -0.0001

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 865

Text #11

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5671. Min Act: -0.0001

Data Index: 720410 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5734. Min Act: -0.0001

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5562. Min Act: -0.0001

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5816. Min Act: -0.0001

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5617. Min Act: -0.0001

Data Index: 946452 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5426. Min Act: -0.0001

Data Index: 189046 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5507. Min Act: -0.0001

Data Index: 1043865 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5527. Min Act: -0.0001

Data Index: 1309644 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.7986. Min Range: -0.7986

Max Act: 0.5249. Min Act: -0.0001

Data Index: 1175887 (C4 (Web Text))

Max Activating Token Index: 916