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

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

Neuron 2305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.6906. Min Act: -0.0000

Data Index: 848263 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.5443. Min Act: -0.0000

Data Index: 617177 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.4401. Min Act: -0.0000

Data Index: 101436 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.4061. Min Act: -0.0000

Data Index: 588928 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3489. Min Act: -0.0000

Data Index: 382641 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.3199. Min Act: -0.0000

Data Index: 419860 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.2177. Min Act: -0.0000

Data Index: 958027 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 1.6906. Min Range: -1.6906

Max Act: 0.9597. Min Act: -0.0001

Data Index: 532752 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1289255 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1098056 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1639. Min Act: -0.0000

Data Index: 1055925 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1513. Min Act: -0.0000

Data Index: 443679 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1165. Min Act: 0.0000

Data Index: 699572 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1631. Min Act: -0.0000

Data Index: 532500 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1352. Min Act: -0.0000

Data Index: 1219681 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1297. Min Act: -0.0000

Data Index: 1028919 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1163. Min Act: -0.0000

Data Index: 708402 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.0999. Min Act: 0.0000

Data Index: 786516 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.1015. Min Act: -0.0000

Data Index: 934415 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 1.6906. Min Range: -1.6906

Max Act: 1.0430. Min Act: -0.0000

Data Index: 895025 (C4 (Web Text))

Max Activating Token Index: 101