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

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

Neuron 4922 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: 2.0926. Min Range: -2.0926

Max Act: 2.0926. Min Act: -0.0000

Data Index: 9879 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.0926. Min Range: -2.0926

Max Act: 2.0287. Min Act: -0.0000

Data Index: 174640 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.6542. Min Act: -0.0000

Data Index: 522321 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.5472. Min Act: -0.0000

Data Index: 269338 (C4 (Web Text))

Max Activating Token Index: 922

Text #4

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3601. Min Act: -0.0000

Data Index: 880263 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.4192. Min Act: -0.0000

Data Index: 136861 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.4110. Min Act: -0.0000

Data Index: 1188323 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.4688. Min Act: 0.0000

Data Index: 1543301 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1101881 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3618. Min Act: -0.0000

Data Index: 961384 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.2933. Min Act: 0.0000

Data Index: 753910 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.4425. Min Act: 0.0000

Data Index: 1254278 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3441. Min Act: -0.0000

Data Index: 890764 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1171014 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1173086 (C4 (Web Text))

Max Activating Token Index: 858

Text #15

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1619647 (Python Code)

Max Activating Token Index: 244

Text #16

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3276. Min Act: 0.0000

Data Index: 1359596 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3028. Min Act: -0.0000

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3061. Min Act: -0.0000

Data Index: 861237 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 2.0926. Min Range: -2.0926

Max Act: 1.3064. Min Act: -0.0000

Data Index: 132292 (C4 (Web Text))

Max Activating Token Index: 614