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

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

Neuron 3519 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: 0.5847. Min Range: -0.5847

Max Act: 0.5847. Min Act: -0.0000

Data Index: 666227 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1120395 (C4 (Web Text))

Max Activating Token Index: 937

Text #2

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5608. Min Act: -0.0000

Data Index: 1284571 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5454. Min Act: -0.0001

Data Index: 396826 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1037102 (C4 (Web Text))

Max Activating Token Index: 1018

Text #5

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5490. Min Act: -0.0001

Data Index: 281676 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5007. Min Act: -0.0000

Data Index: 509837 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4860. Min Act: -0.0001

Data Index: 1329954 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5396. Min Act: -0.0000

Data Index: 294405 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4982. Min Act: -0.0000

Data Index: 111435 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4956. Min Act: -0.0000

Data Index: 563311 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1250071 (C4 (Web Text))

Max Activating Token Index: 372

Text #12

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4796. Min Act: -0.0000

Data Index: 852539 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4827. Min Act: -0.0000

Data Index: 387555 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4968. Min Act: -0.0000

Data Index: 607722 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4677. Min Act: -0.0000

Data Index: 544421 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1220936 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4809. Min Act: -0.0000

Data Index: 282728 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1013171 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.5847. Min Range: -0.5847

Max Act: 0.4557. Min Act: -0.0001

Data Index: 196753 (C4 (Web Text))

Max Activating Token Index: 26