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

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

Neuron 5016 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: 11.4350. Min Range: -11.4350

Max Act: 11.4350. Min Act: -0.0000

Data Index: 367977 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 11.4350. Min Range: -11.4350

Max Act: 9.4234. Min Act: -0.0000

Data Index: 284976 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 11.4350. Min Range: -11.4350

Max Act: 8.0271. Min Act: -0.0000

Data Index: 298801 (C4 (Web Text))

Max Activating Token Index: 407

Text #3

Max Range: 11.4350. Min Range: -11.4350

Max Act: 7.2906. Min Act: -0.0000

Data Index: 538090 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.1704. Min Act: -0.0000

Data Index: 954238 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 11.4350. Min Range: -11.4350

Max Act: 6.5303. Min Act: -0.0000

Data Index: 92710 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 11.4350. Min Range: -11.4350

Max Act: 7.2614. Min Act: -0.0000

Data Index: 1142454 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 11.4350. Min Range: -11.4350

Max Act: 6.7812. Min Act: -0.0000

Data Index: 793597 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.6325. Min Act: -0.0000

Data Index: 601992 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.3924. Min Act: -0.0000

Data Index: 475444 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 11.4350. Min Range: -11.4350

Max Act: 4.7687. Min Act: -0.0000

Data Index: 231439 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 11.4350. Min Range: -11.4350

Max Act: 6.1343. Min Act: -0.0000

Data Index: 1284833 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.1957. Min Act: -0.0000

Data Index: 215717 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.0734. Min Act: -0.0000

Data Index: 274835 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 11.4350. Min Range: -11.4350

Max Act: 5.2552. Min Act: -0.0000

Data Index: 834949 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 11.4350. Min Range: -11.4350

Max Act: 4.3357. Min Act: -0.0000

Data Index: 496933 (C4 (Web Text))

Max Activating Token Index: 671

Text #16

Max Range: 11.4350. Min Range: -11.4350

Max Act: 4.6287. Min Act: -0.0000

Data Index: 943622 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 11.4350. Min Range: -11.4350

Max Act: 2.8423. Min Act: -0.0000

Data Index: 525238 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 11.4350. Min Range: -11.4350

Max Act: 3.7045. Min Act: -0.0000

Data Index: 1250636 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 11.4350. Min Range: -11.4350

Max Act: 3.5039. Min Act: -0.0000

Data Index: 1025331 (C4 (Web Text))

Max Activating Token Index: 998