Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.5291. Min Act: -0.0000

Data Index: 519426 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.3772. Min Act: -0.0001

Data Index: 530217 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.3743. Min Act: -0.0001

Data Index: 770804 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.2604. Min Act: -0.0001

Data Index: 388474 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1983. Min Act: -0.0001

Data Index: 1073218 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.2183. Min Act: -0.0001

Data Index: 115159 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1775. Min Act: -0.0000

Data Index: 114998 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1740. Min Act: -0.0001

Data Index: 528858 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0757. Min Act: -0.0001

Data Index: 112079 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.2072. Min Act: -0.0001

Data Index: 736296 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1318. Min Act: -0.0001

Data Index: 259568 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1185. Min Act: -0.0000

Data Index: 768691 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1792. Min Act: -0.0001

Data Index: 659193 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1037. Min Act: -0.0000

Data Index: 263014 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0981. Min Act: -0.0001

Data Index: 306127 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.1130. Min Act: -0.0001

Data Index: 64139 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0101. Min Act: -0.0001

Data Index: 699045 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0676. Min Act: -0.0000

Data Index: 948806 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0470. Min Act: -0.0001

Data Index: 1168956 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.5291. Min Range: -1.5291

Max Act: 1.0507. Min Act: -0.0000

Data Index: 451656 (C4 (Web Text))

Max Activating Token Index: 589