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

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

Neuron 1032 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: 4.4520. Min Range: -4.4520

Max Act: 4.4520. Min Act: -0.0000

Data Index: 1274050 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 4.4520. Min Range: -4.4520

Max Act: 4.2072. Min Act: -0.0000

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 4.4520. Min Range: -4.4520

Max Act: 4.2619. Min Act: -0.0000

Data Index: 1204460 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.8137. Min Act: -0.0000

Data Index: 1232912 (C4 (Web Text))

Max Activating Token Index: 804

Text #4

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.9570. Min Act: -0.0000

Data Index: 750298 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.8226. Min Act: -0.0000

Data Index: 205371 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.9912. Min Act: -0.0000

Data Index: 1148890 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.1936. Min Act: -0.0000

Data Index: 757295 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0891. Min Act: -0.0000

Data Index: 86116 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.2247. Min Act: -0.0000

Data Index: 1053109 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.1787. Min Act: -0.0000

Data Index: 1247608 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0373. Min Act: -0.0000

Data Index: 427619 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0193. Min Act: -0.0000

Data Index: 810615 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.1667. Min Act: -0.0000

Data Index: 1003251 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0874. Min Act: -0.0000

Data Index: 1296436 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0404. Min Act: -0.0000

Data Index: 1147085 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 4.4520. Min Range: -4.4520

Max Act: 3.0320. Min Act: -0.0000

Data Index: 556770 (C4 (Web Text))

Max Activating Token Index: 495

Text #17

Max Range: 4.4520. Min Range: -4.4520

Max Act: 2.8950. Min Act: -0.0000

Data Index: 195342 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 4.4520. Min Range: -4.4520

Max Act: 2.8639. Min Act: -0.0000

Data Index: 926084 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 4.4520. Min Range: -4.4520

Max Act: 2.9936. Min Act: -0.0000

Data Index: 350050 (C4 (Web Text))

Max Activating Token Index: 234