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

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

Neuron 4701 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6867. Min Act: -0.0000

Data Index: 644111 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.7037. Min Act: -0.0000

Data Index: 326259 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6775. Min Act: -0.0000

Data Index: 730809 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5798. Min Act: -0.0000

Data Index: 156899 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.6153. Min Act: -0.0000

Data Index: 200183 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4431. Min Act: -0.0000

Data Index: 183297 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5320. Min Act: -0.0000

Data Index: 790114 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5527. Min Act: -0.0000

Data Index: 1644666 (Python Code)

Max Activating Token Index: 263

Text #8

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4451. Min Act: -0.0000

Data Index: 949764 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5176. Min Act: -0.0000

Data Index: 259444 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4486. Min Act: -0.0000

Data Index: 261451 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4755. Min Act: -0.0000

Data Index: 1048130 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5406. Min Act: -0.0000

Data Index: 570704 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4810. Min Act: -0.0000

Data Index: 871325 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4846. Min Act: -0.0000

Data Index: 175556 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4472. Min Act: -0.0000

Data Index: 1049120 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1192227 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4465. Min Act: -0.0000

Data Index: 122413 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4778. Min Act: -0.0000

Data Index: 493200 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.7037. Min Range: -0.7037

Max Act: 0.4957. Min Act: -0.0000

Data Index: 701059 (C4 (Web Text))

Max Activating Token Index: 829