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

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

Neuron 5666 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7367. Min Range: -4.7367

Max Act: 4.7367. Min Act: -0.0000

Data Index: 75813 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.5267. Min Act: -0.0000

Data Index: 393886 (C4 (Web Text))

Max Activating Token Index: 324

Text #2

Max Range: 4.7367. Min Range: -4.7367

Max Act: 4.2890. Min Act: -0.0000

Data Index: 1396772 (Python Code)

Max Activating Token Index: 511

Text #3

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.7724. Min Act: -0.0000

Data Index: 997221 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.9762. Min Act: -0.0000

Data Index: 456087 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.7780. Min Act: -0.0000

Data Index: 1115990 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.9395. Min Act: -0.0000

Data Index: 35202 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.5458. Min Act: -0.0000

Data Index: 343023 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.8973. Min Act: -0.0000

Data Index: 163332 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.5915. Min Act: -0.0000

Data Index: 193875 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.6921. Min Act: -0.0000

Data Index: 802989 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.5164. Min Act: -0.0000

Data Index: 636102 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.6404. Min Act: -0.0000

Data Index: 124786 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.6315. Min Act: -0.0000

Data Index: 376831 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.5083. Min Act: -0.0000

Data Index: 970254 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.4297. Min Act: -0.0000

Data Index: 1273089 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.4225. Min Act: -0.0000

Data Index: 1105041 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.4174. Min Act: -0.0000

Data Index: 469678 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.0883. Min Act: -0.0000

Data Index: 1127941 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 4.7367. Min Range: -4.7367

Max Act: 3.2122. Min Act: -0.0000

Data Index: 50587 (C4 (Web Text))

Max Activating Token Index: 344