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

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

Neuron 2178 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: 3.2774. Min Range: -3.2774

Max Act: 3.2774. Min Act: -0.0000

Data Index: 577757 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.9299. Min Act: -0.0000

Data Index: 68303 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.9272. Min Act: -0.0000

Data Index: 94768 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.9184. Min Act: -0.0000

Data Index: 295613 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.9134. Min Act: -0.0000

Data Index: 315866 (C4 (Web Text))

Max Activating Token Index: 337

Text #5

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.4947. Min Act: -0.0000

Data Index: 612951 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.5197. Min Act: -0.0000

Data Index: 798126 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.3461. Min Act: -0.0000

Data Index: 1283390 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.5069. Min Act: -0.0000

Data Index: 743994 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.5068. Min Act: -0.0000

Data Index: 499234 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.4729. Min Act: -0.0000

Data Index: 859863 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.4676. Min Act: -0.0000

Data Index: 1182025 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.4446. Min Act: -0.0000

Data Index: 1307039 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.5079. Min Act: -0.0000

Data Index: 286707 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.3428. Min Act: -0.0000

Data Index: 679938 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.3375. Min Act: -0.0000

Data Index: 1107106 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.1815. Min Act: -0.0000

Data Index: 347099 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.4829. Min Act: -0.0000

Data Index: 259679 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.1005. Min Act: -0.0000

Data Index: 1094002 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 3.2774. Min Range: -3.2774

Max Act: 2.2926. Min Act: -0.0000

Data Index: 290665 (C4 (Web Text))

Max Activating Token Index: 678