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

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

Neuron 1408 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: 0.4996. Min Range: -0.4996

Max Act: 0.4927. Min Act: -0.0000

Data Index: 415619 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4498. Min Act: -0.0000

Data Index: 885288 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1124481 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4341. Min Act: -0.0000

Data Index: 875263 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4398. Min Act: -0.0000

Data Index: 744181 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4485. Min Act: -0.0000

Data Index: 958862 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4375. Min Act: -0.0000

Data Index: 766639 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4401. Min Act: -0.0000

Data Index: 787361 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1338238 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4208. Min Act: -0.0000

Data Index: 636608 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4135. Min Act: -0.0000

Data Index: 45813 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1178959 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1316255 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3711. Min Act: -0.0000

Data Index: 783480 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1244869 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3890. Min Act: -0.0000

Data Index: 374579 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3761. Min Act: -0.0000

Data Index: 613745 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3690. Min Act: -0.0000

Data Index: 924298 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3982. Min Act: -0.0000

Data Index: 869340 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.4996. Min Range: -0.4996

Max Act: 0.3655. Min Act: -0.0000

Data Index: 506833 (C4 (Web Text))

Max Activating Token Index: 829