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

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

Neuron 5683 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1070835 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7029. Min Act: -0.0000

Data Index: 51547 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.7182. Min Act: -0.0000

Data Index: 279726 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6576. Min Act: -0.0000

Data Index: 696647 (C4 (Web Text))

Max Activating Token Index: 637

Text #4

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.6720. Min Act: -0.0000

Data Index: 389263 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1085124 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.5249. Min Act: -0.0000

Data Index: 812081 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.5213. Min Act: -0.0000

Data Index: 958371 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4962. Min Act: 0.0001

Data Index: 578744 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3940. Min Act: -0.0000

Data Index: 276858 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1002245 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1224430 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4259. Min Act: 0.0000

Data Index: 468019 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3969. Min Act: -0.0000

Data Index: 956238 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3933. Min Act: -0.0000

Data Index: 943601 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4095. Min Act: -0.0000

Data Index: 70944 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3853. Min Act: -0.0000

Data Index: 128266 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.4363. Min Act: 0.0000

Data Index: 220189 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3819. Min Act: 0.0000

Data Index: 15722 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.8956. Min Range: -0.8956

Max Act: 0.3718. Min Act: 0.0000

Data Index: 1014748 (C4 (Web Text))

Max Activating Token Index: 574