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

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

Neuron 5236 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.4633. Min Act: -0.0000

Data Index: 183711 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9881. Min Act: -0.0000

Data Index: 563603 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.3244. Min Act: -0.0000

Data Index: 1074301 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.1399. Min Act: -0.0000

Data Index: 1388405 (Python Code)

Max Activating Token Index: 794

Text #4

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.2159. Min Act: -0.0000

Data Index: 1400033 (Python Code)

Max Activating Token Index: 877

Text #5

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.3139. Min Act: -0.0000

Data Index: 1599078 (Python Code)

Max Activating Token Index: 81

Text #6

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.1546. Min Act: -0.0000

Data Index: 63645 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.0074. Min Act: -0.0000

Data Index: 123119 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.1004. Min Act: -0.0000

Data Index: 65876 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9969. Min Act: -0.0000

Data Index: 876254 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.2069. Min Act: -0.0000

Data Index: 740407 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9661. Min Act: -0.0000

Data Index: 674630 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.0746. Min Act: -0.0000

Data Index: 260482 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9457. Min Act: -0.0000

Data Index: 1576932 (Python Code)

Max Activating Token Index: 721

Text #14

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9267. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 2.4633. Min Range: -2.4633

Max Act: 2.0035. Min Act: -0.0000

Data Index: 956392 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9848. Min Act: -0.0000

Data Index: 386087 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.8792. Min Act: -0.0000

Data Index: 359870 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9641. Min Act: -0.0000

Data Index: 246241 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 2.4633. Min Range: -2.4633

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1409528 (Python Code)

Max Activating Token Index: 924