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

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

Neuron 2203 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.7992. Min Act: -0.0000

Data Index: 395942 (C4 (Web Text))

Max Activating Token Index: 1006

Text #1

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.6073. Min Act: -0.0000

Data Index: 406189 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5466. Min Act: -0.0000

Data Index: 778564 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1131934 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1071231 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.4648. Min Act: -0.0000

Data Index: 205010 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1223281 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.4210. Min Act: -0.0000

Data Index: 1249695 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.4235. Min Act: -0.0000

Data Index: 127633 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3858. Min Act: -0.0000

Data Index: 138357 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.4046. Min Act: -0.0000

Data Index: 852573 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3527. Min Act: -0.0000

Data Index: 200134 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3464. Min Act: -0.0000

Data Index: 431927 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3370. Min Act: -0.0000

Data Index: 742491 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3574. Min Act: -0.0000

Data Index: 400050 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3157. Min Act: -0.0000

Data Index: 646246 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3350. Min Act: -0.0000

Data Index: 177447 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3199. Min Act: -0.0000

Data Index: 1220701 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3181. Min Act: -0.0000

Data Index: 1156260 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.7992. Min Range: -0.7992

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1024005 (C4 (Web Text))

Max Activating Token Index: 254