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

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

Neuron 1828 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.3438. Min Act: -0.0000

Data Index: 705709 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1835. Min Act: -0.0000

Data Index: 1243962 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.3146. Min Act: -0.0000

Data Index: 259165 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.3932. Min Act: -0.0000

Data Index: 237808 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.2482. Min Act: -0.0000

Data Index: 70223 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1355402 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1841. Min Act: -0.0000

Data Index: 311125 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1197. Min Act: -0.0000

Data Index: 968569 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1232661 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1494. Min Act: -0.0000

Data Index: 623097 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.2346. Min Act: -0.0000

Data Index: 384863 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.2244. Min Act: -0.0000

Data Index: 310114 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0958. Min Act: -0.0000

Data Index: 1249879 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0903. Min Act: -0.0000

Data Index: 722171 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.1421. Min Act: -0.0000

Data Index: 56320 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1130799 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0498. Min Act: -0.0000

Data Index: 308901 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1197676 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0253. Min Act: -0.0000

Data Index: 488013 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.3932. Min Range: -1.3932

Max Act: 1.0636. Min Act: 0.0000

Data Index: 580221 (C4 (Web Text))

Max Activating Token Index: 604