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

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

Neuron 5780 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: 0.6903. Min Range: -0.6903

Max Act: 0.6903. Min Act: 0.0000

Data Index: 1097046 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4981. Min Act: -0.0000

Data Index: 954536 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.5037. Min Act: -0.0000

Data Index: 475044 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1336730 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1160831 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1056873 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3913. Min Act: -0.0000

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3884. Min Act: -0.0000

Data Index: 191953 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1086746 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4088. Min Act: -0.0000

Data Index: 112405 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.4067. Min Act: -0.0000

Data Index: 152198 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3926. Min Act: -0.0000

Data Index: 123374 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3588. Min Act: -0.0000

Data Index: 731264 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3567. Min Act: -0.0000

Data Index: 735206 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3499. Min Act: -0.0000

Data Index: 352496 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3447. Min Act: 0.0000

Data Index: 896566 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3425. Min Act: -0.0000

Data Index: 964315 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3433. Min Act: -0.0000

Data Index: 193740 (C4 (Web Text))

Max Activating Token Index: 288

Text #18

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3386. Min Act: -0.0000

Data Index: 960430 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.6903. Min Range: -0.6903

Max Act: 0.3245. Min Act: -0.0000

Data Index: 191556 (C4 (Web Text))

Max Activating Token Index: 927