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

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

Neuron 1211 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7930. Min Act: -0.0001

Data Index: 241206 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1213623 (C4 (Web Text))

Max Activating Token Index: 855

Text #2

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7962. Min Act: -0.0000

Data Index: 320470 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7170. Min Act: -0.0000

Data Index: 17576 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7314. Min Act: -0.0001

Data Index: 759164 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.7236. Min Act: -0.0000

Data Index: 1261210 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6636. Min Act: -0.0001

Data Index: 901303 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6545. Min Act: -0.0001

Data Index: 332950 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6872. Min Act: -0.0000

Data Index: 662063 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6608. Min Act: -0.0000

Data Index: 861313 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6174. Min Act: -0.0001

Data Index: 887887 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6363. Min Act: -0.0000

Data Index: 39631 (C4 (Web Text))

Max Activating Token Index: 878

Text #12

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1052584 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6096. Min Act: -0.0001

Data Index: 164217 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6361. Min Act: -0.0000

Data Index: 448383 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1350243 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1195419 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6189. Min Act: -0.0001

Data Index: 938748 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.5895. Min Act: -0.0000

Data Index: 827752 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.7962. Min Range: -0.7962

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1041089 (C4 (Web Text))

Max Activating Token Index: 696