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

Dataset: The Pile

Neuron 4132 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.5683. Min Act: -0.0000

Data Index: 1602164 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.6867. Min Act: -0.0000

Data Index: 732643 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.5973. Min Act: -0.0000

Data Index: 136678 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1470996 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.3779. Min Act: 0.0000

Data Index: 1838451 (The Pile)

Max Activating Token Index: 230

Text #5

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.3605. Min Act: -0.0000

Data Index: 1838583 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1528681 (The Pile)

Max Activating Token Index: 343

Text #7

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.2666. Min Act: -0.0000

Data Index: 1582467 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.2934. Min Act: 0.0000

Data Index: 1227532 (The Pile)

Max Activating Token Index: 431

Text #9

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1071402 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1084543 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.2280. Min Act: -0.0000

Data Index: 649708 (The Pile)

Max Activating Token Index: 222

Text #12

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1327784 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.1915. Min Act: -0.0000

Data Index: 1194293 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.2547. Min Act: -0.0000

Data Index: 1540270 (The Pile)

Max Activating Token Index: 165

Text #15

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.1667. Min Act: -0.0000

Data Index: 901742 (The Pile)

Max Activating Token Index: 542

Text #16

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.1312. Min Act: -0.0000

Data Index: 1457400 (The Pile)

Max Activating Token Index: 138

Text #17

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.0540. Min Act: 0.0000

Data Index: 1053578 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.0479. Min Act: -0.0000

Data Index: 682984 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 1.6867. Min Range: -1.6867

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1591084 (The Pile)

Max Activating Token Index: 931