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

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

Neuron 3838 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.7412. Min Act: -0.0000

Data Index: 1331209 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.7389. Min Act: -0.0001

Data Index: 55428 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6916. Min Act: -0.0000

Data Index: 304141 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.6539. Min Act: -0.0001

Data Index: 1105654 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5590. Min Act: -0.0001

Data Index: 871873 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1093009 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5095. Min Act: -0.0001

Data Index: 473064 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5662. Min Act: -0.0001

Data Index: 922638 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5742. Min Act: -0.0001

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5222. Min Act: -0.0000

Data Index: 245063 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5374. Min Act: -0.0000

Data Index: 754704 (C4 (Web Text))

Max Activating Token Index: 677

Text #11

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5484. Min Act: -0.0000

Data Index: 357505 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5319. Min Act: -0.0001

Data Index: 342749 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5312. Min Act: -0.0000

Data Index: 402604 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.4801. Min Act: -0.0001

Data Index: 1143615 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5283. Min Act: -0.0000

Data Index: 347755 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5258. Min Act: -0.0000

Data Index: 993985 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5179. Min Act: -0.0000

Data Index: 383966 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.5171. Min Act: -0.0001

Data Index: 800143 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.7412. Min Range: -0.7412

Max Act: 0.4658. Min Act: -0.0000

Data Index: 265716 (C4 (Web Text))

Max Activating Token Index: 598