Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3632. Min Act: -0.0000

Data Index: 163539 (C4 (Web Text))

Max Activating Token Index: 467

Text #1

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3569. Min Act: -0.0000

Data Index: 1259099 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1294184 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1389169 (Python Code)

Max Activating Token Index: 1022

Text #4

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3186. Min Act: -0.0000

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3295. Min Act: -0.0001

Data Index: 469032 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2751. Min Act: -0.0001

Data Index: 355957 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3143. Min Act: -0.0000

Data Index: 875813 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3110. Min Act: -0.0001

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.3012. Min Act: -0.0001

Data Index: 505583 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2877. Min Act: -0.0001

Data Index: 740247 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2783. Min Act: -0.0001

Data Index: 1358431 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2868. Min Act: -0.0001

Data Index: 684695 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2803. Min Act: -0.0000

Data Index: 237734 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2809. Min Act: -0.0000

Data Index: 783543 (C4 (Web Text))

Max Activating Token Index: 527

Text #15

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2900. Min Act: -0.0001

Data Index: 504794 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2803. Min Act: -0.0001

Data Index: 774862 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2882. Min Act: -0.0001

Data Index: 1155229 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2592. Min Act: -0.0001

Data Index: 486971 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.3632. Min Range: -0.3632

Max Act: 0.2765. Min Act: -0.0001

Data Index: 681737 (C4 (Web Text))

Max Activating Token Index: 533