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

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

Neuron 4832 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: 2.0925. Min Range: -2.0925

Max Act: 2.0925. Min Act: -0.0000

Data Index: 957878 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.7277. Min Act: -0.0001

Data Index: 916061 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.6589. Min Act: -0.0001

Data Index: 44327 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.5350. Min Act: -0.0000

Data Index: 684584 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.4042. Min Act: -0.0001

Data Index: 828477 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.4051. Min Act: -0.0000

Data Index: 210882 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.3830. Min Act: -0.0000

Data Index: 1311583 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.3849. Min Act: -0.0001

Data Index: 640335 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.3207. Min Act: -0.0000

Data Index: 1062397 (C4 (Web Text))

Max Activating Token Index: 30

Text #9

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2971. Min Act: -0.0000

Data Index: 878822 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1068495 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2725. Min Act: -0.0001

Data Index: 49954 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2588. Min Act: -0.0001

Data Index: 597560 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2882. Min Act: -0.0000

Data Index: 1146657 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.2239. Min Act: -0.0000

Data Index: 1327423 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.1873. Min Act: -0.0000

Data Index: 103356 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.1942. Min Act: -0.0001

Data Index: 438441 (C4 (Web Text))

Max Activating Token Index: 695

Text #17

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.1851. Min Act: -0.0001

Data Index: 921181 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.1755. Min Act: -0.0001

Data Index: 237299 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 2.0925. Min Range: -2.0925

Max Act: 1.0993. Min Act: -0.0001

Data Index: 287148 (C4 (Web Text))

Max Activating Token Index: 317