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

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

Neuron 5676 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3237. Min Act: -0.0000

Data Index: 1054984 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3321. Min Act: -0.0000

Data Index: 431385 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1290887 (C4 (Web Text))

Max Activating Token Index: 472

Text #3

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3027. Min Act: -0.0000

Data Index: 517197 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.3020. Min Act: -0.0000

Data Index: 791964 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2730. Min Act: -0.0000

Data Index: 648420 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2656. Min Act: -0.0000

Data Index: 404656 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1340103 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1165185 (C4 (Web Text))

Max Activating Token Index: 622

Text #9

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2641. Min Act: -0.0000

Data Index: 669032 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2565. Min Act: -0.0000

Data Index: 989098 (C4 (Web Text))

Max Activating Token Index: 543

Text #12

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2500. Min Act: -0.0000

Data Index: 911193 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2367. Min Act: -0.0000

Data Index: 1458109 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2383. Min Act: -0.0000

Data Index: 575225 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2296. Min Act: -0.0000

Data Index: 1546251 (Python Code)

Max Activating Token Index: 966

Text #16

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.1933. Min Act: -0.0000

Data Index: 293546 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2328. Min Act: -0.0000

Data Index: 210358 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1215467 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.3321. Min Range: -0.3321

Max Act: 0.2067. Min Act: -0.0000

Data Index: 657165 (C4 (Web Text))

Max Activating Token Index: 621