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

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

Neuron 2172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3585. Min Act: -0.0000

Data Index: 960113 (C4 (Web Text))

Max Activating Token Index: 785

Text #1

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3535. Min Act: -0.0000

Data Index: 927659 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1236339 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3310. Min Act: -0.0000

Data Index: 446028 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3318. Min Act: -0.0000

Data Index: 1308143 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3009. Min Act: -0.0000

Data Index: 324989 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3011. Min Act: -0.0000

Data Index: 1152312 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2957. Min Act: -0.0000

Data Index: 87072 (C4 (Web Text))

Max Activating Token Index: 625

Text #8

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2978. Min Act: -0.0001

Data Index: 1333938 (C4 (Web Text))

Max Activating Token Index: 320

Text #9

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1054639 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2755. Min Act: -0.0000

Data Index: 11127 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2780. Min Act: -0.0000

Data Index: 281157 (C4 (Web Text))

Max Activating Token Index: 951

Text #12

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2709. Min Act: -0.0000

Data Index: 541631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2788. Min Act: -0.0000

Data Index: 351355 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2842. Min Act: -0.0000

Data Index: 650249 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2681. Min Act: -0.0001

Data Index: 935523 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2700. Min Act: -0.0000

Data Index: 800536 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2677. Min Act: -0.0000

Data Index: 830508 (C4 (Web Text))

Max Activating Token Index: 983

Text #18

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1108599 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2707. Min Act: -0.0000

Data Index: 855772 (C4 (Web Text))

Max Activating Token Index: 70