Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.6179. Min Act: -0.0001

Data Index: 172114 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1401471 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5338. Min Act: -0.0000

Data Index: 150700 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1534738 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5078. Min Act: -0.0000

Data Index: 439098 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5113. Min Act: -0.0000

Data Index: 980933 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4891. Min Act: -0.0000

Data Index: 238880 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.5014. Min Act: -0.0001

Data Index: 1603567 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4683. Min Act: -0.0000

Data Index: 625649 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4620. Min Act: -0.0001

Data Index: 1635039 (Python Code)

Max Activating Token Index: 868

Text #10

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1336318 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4211. Min Act: -0.0001

Data Index: 1364988 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4466. Min Act: -0.0001

Data Index: 1554309 (Python Code)

Max Activating Token Index: 364

Text #13

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4326. Min Act: -0.0001

Data Index: 1443902 (Python Code)

Max Activating Token Index: 938

Text #14

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4642. Min Act: -0.0000

Data Index: 860137 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4570. Min Act: -0.0001

Data Index: 1628010 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4368. Min Act: -0.0000

Data Index: 53459 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.3968. Min Act: -0.0000

Data Index: 382126 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4071. Min Act: -0.0001

Data Index: 1590746 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.6179. Min Range: -0.6179

Max Act: 0.4042. Min Act: -0.0000

Data Index: 197975 (C4 (Web Text))

Max Activating Token Index: 781