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

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

Neuron 5407 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4970. Min Range: -3.4970

Max Act: 3.4970. Min Act: -0.0000

Data Index: 1025036 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 3.4970. Min Range: -3.4970

Max Act: 3.1845. Min Act: -0.0000

Data Index: 1088648 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.8785. Min Act: -0.0000

Data Index: 488773 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.7754. Min Act: -0.0000

Data Index: 642527 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.7637. Min Act: -0.0000

Data Index: 524303 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.5849. Min Act: -0.0000

Data Index: 849873 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.4404. Min Act: -0.0000

Data Index: 1078355 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.5310. Min Act: -0.0000

Data Index: 488717 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.6903. Min Act: -0.0000

Data Index: 1195998 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.6659. Min Act: -0.0000

Data Index: 1350618 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.4235. Min Act: -0.0000

Data Index: 395116 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.4043. Min Act: -0.0000

Data Index: 1190450 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.2815. Min Act: -0.0000

Data Index: 316537 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.3294. Min Act: -0.0000

Data Index: 1038489 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 3.4970. Min Range: -3.4970

Max Act: 1.9921. Min Act: -0.0000

Data Index: 236853 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.3053. Min Act: -0.0000

Data Index: 528842 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.1548. Min Act: -0.0000

Data Index: 884354 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.3310. Min Act: -0.0000

Data Index: 457564 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.3399. Min Act: -0.0000

Data Index: 226915 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 3.4970. Min Range: -3.4970

Max Act: 2.1939. Min Act: -0.0000

Data Index: 601047 (C4 (Web Text))

Max Activating Token Index: 567