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

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

Neuron 4507 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2701. Min Act: -0.0000

Data Index: 478233 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2517. Min Act: -0.0000

Data Index: 313507 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2222. Min Act: -0.0000

Data Index: 321073 (C4 (Web Text))

Max Activating Token Index: 942

Text #3

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2201. Min Act: -0.0000

Data Index: 1267750 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0437. Min Act: -0.0000

Data Index: 519073 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1392. Min Act: -0.0000

Data Index: 862637 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0970. Min Act: -0.0000

Data Index: 472027 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1194824 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.2965. Min Act: -0.0000

Data Index: 877121 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.0627. Min Act: -0.0000

Data Index: 189053 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.2965. Min Range: -1.2965

Max Act: 1.1143. Min Act: -0.0000

Data Index: 472131 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9892. Min Act: -0.0000

Data Index: 553647 (C4 (Web Text))

Max Activating Token Index: 1013

Text #12

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9551. Min Act: -0.0000

Data Index: 171684 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9396. Min Act: -0.0000

Data Index: 87612 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9281. Min Act: -0.0000

Data Index: 184629 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.9377. Min Act: -0.0000

Data Index: 120640 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.8587. Min Act: -0.0000

Data Index: 864283 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.8875. Min Act: -0.0000

Data Index: 229619 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.8822. Min Act: -0.0000

Data Index: 584259 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 1.2965. Min Range: -1.2965

Max Act: 0.8732. Min Act: -0.0000

Data Index: 988784 (C4 (Web Text))

Max Activating Token Index: 628