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

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

Neuron 4492 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: 2.6442. Min Range: -2.6442

Max Act: 2.6442. Min Act: -0.0000

Data Index: 48622 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 2.6442. Min Range: -2.6442

Max Act: 2.1761. Min Act: -0.0000

Data Index: 354622 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.8169. Min Act: -0.0000

Data Index: 357323 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1493364 (Python Code)

Max Activating Token Index: 626

Text #4

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1330272 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.6394. Min Act: -0.0000

Data Index: 171455 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.7339. Min Act: -0.0000

Data Index: 985724 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5943. Min Act: -0.0000

Data Index: 1146127 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5454. Min Act: -0.0000

Data Index: 1184997 (C4 (Web Text))

Max Activating Token Index: 370

Text #10

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5242. Min Act: -0.0000

Data Index: 631591 (C4 (Web Text))

Max Activating Token Index: 840

Text #11

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5290. Min Act: -0.0000

Data Index: 676347 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.6057. Min Act: -0.0000

Data Index: 497262 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5320. Min Act: -0.0000

Data Index: 1152405 (C4 (Web Text))

Max Activating Token Index: 962

Text #14

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5787. Min Act: -0.0000

Data Index: 1040923 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5050. Min Act: -0.0000

Data Index: 551703 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1139511 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5147. Min Act: -0.0000

Data Index: 1163630 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1150255 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 2.6442. Min Range: -2.6442

Max Act: 1.5206. Min Act: -0.0000

Data Index: 12845 (C4 (Web Text))

Max Activating Token Index: 854