Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.9157. Min Range: -5.9157

Max Act: 5.9157. Min Act: -0.0000

Data Index: 462745 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 5.9157. Min Range: -5.9157

Max Act: 5.4235. Min Act: -0.0000

Data Index: 205506 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 5.9157. Min Range: -5.9157

Max Act: 5.3829. Min Act: -0.0000

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 5.9157. Min Range: -5.9157

Max Act: 5.0403. Min Act: -0.0000

Data Index: 370870 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.8841. Min Act: -0.0000

Data Index: 1341192 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.6269. Min Act: -0.0000

Data Index: 267052 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.8830. Min Act: -0.0000

Data Index: 429299 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.4705. Min Act: -0.0000

Data Index: 666737 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.9713. Min Act: -0.0000

Data Index: 176909 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.5128. Min Act: -0.0000

Data Index: 331505 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.6499. Min Act: -0.0000

Data Index: 511973 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.6129. Min Act: -0.0000

Data Index: 275902 (C4 (Web Text))

Max Activating Token Index: 232

Text #12

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.3452. Min Act: -0.0000

Data Index: 702506 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.5137. Min Act: -0.0000

Data Index: 553541 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.3131. Min Act: -0.0000

Data Index: 724602 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.2361. Min Act: -0.0000

Data Index: 559231 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 5.9157. Min Range: -5.9157

Max Act: 3.8712. Min Act: -0.0000

Data Index: 87081 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 5.9157. Min Range: -5.9157

Max Act: 3.9961. Min Act: -0.0000

Data Index: 322675 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.2116. Min Act: -0.0000

Data Index: 280648 (C4 (Web Text))

Max Activating Token Index: 623

Text #19

Max Range: 5.9157. Min Range: -5.9157

Max Act: 4.0496. Min Act: -0.0000

Data Index: 1059383 (C4 (Web Text))

Max Activating Token Index: 98