Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4522 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5531. Min Act: -0.0000

Data Index: 334975 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5925. Min Act: -0.0000

Data Index: 115104 (C4 (Web Text))

Max Activating Token Index: 1019

Text #2

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5875. Min Act: -0.0000

Data Index: 351395 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5075. Min Act: -0.0000

Data Index: 260826 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5078. Min Act: -0.0000

Data Index: 798528 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.5477. Min Act: -0.0000

Data Index: 255665 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4977. Min Act: -0.0000

Data Index: 590026 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4979. Min Act: -0.0000

Data Index: 80477 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4662. Min Act: -0.0000

Data Index: 204270 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4644. Min Act: -0.0000

Data Index: 1077542 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4615. Min Act: -0.0000

Data Index: 500745 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4611. Min Act: -0.0000

Data Index: 931122 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1307473 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4606. Min Act: -0.0000

Data Index: 176043 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4612. Min Act: -0.0000

Data Index: 1062651 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4567. Min Act: -0.0000

Data Index: 553330 (C4 (Web Text))

Max Activating Token Index: 1008

Text #16

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4995. Min Act: -0.0000

Data Index: 882233 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4546. Min Act: -0.0000

Data Index: 533290 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4967. Min Act: -0.0000

Data Index: 145984 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 1.5925. Min Range: -1.5925

Max Act: 1.4257. Min Act: -0.0000

Data Index: 671548 (C4 (Web Text))

Max Activating Token Index: 1008