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

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

Neuron 3994 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1544. Min Range: -4.1544

Max Act: 4.1544. Min Act: -0.0000

Data Index: 901633 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 4.1544. Min Range: -4.1544

Max Act: 3.0446. Min Act: -0.0000

Data Index: 1289358 (C4 (Web Text))

Max Activating Token Index: 260

Text #2

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.9096. Min Act: -0.0000

Data Index: 166585 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.8481. Min Act: -0.0000

Data Index: 747868 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.6633. Min Act: -0.0000

Data Index: 827565 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.6311. Min Act: -0.0000

Data Index: 687193 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.5485. Min Act: -0.0000

Data Index: 717842 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.5129. Min Act: -0.0000

Data Index: 534410 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.3573. Min Act: -0.0000

Data Index: 111672 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.3973. Min Act: -0.0000

Data Index: 657988 (C4 (Web Text))

Max Activating Token Index: 3

Text #10

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.1975. Min Act: -0.0000

Data Index: 406227 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.1619. Min Act: -0.0000

Data Index: 1155723 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.2854. Min Act: -0.0000

Data Index: 682779 (C4 (Web Text))

Max Activating Token Index: 39

Text #13

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.4037. Min Act: -0.0000

Data Index: 419348 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.2806. Min Act: -0.0000

Data Index: 464024 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.2700. Min Act: -0.0000

Data Index: 760105 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.3942. Min Act: -0.0000

Data Index: 20280 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.2351. Min Act: -0.0000

Data Index: 1271361 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.3295. Min Act: -0.0000

Data Index: 31541 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 4.1544. Min Range: -4.1544

Max Act: 2.0799. Min Act: -0.0000

Data Index: 780927 (C4 (Web Text))

Max Activating Token Index: 829