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

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

Neuron 295 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1590. Min Act: -0.0001

Data Index: 1091995 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9624. Min Act: -0.0001

Data Index: 1266251 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9158. Min Act: -0.0001

Data Index: 1594835 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8870. Min Act: -0.0001

Data Index: 340991 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7958. Min Act: -0.0001

Data Index: 1272479 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8114. Min Act: -0.0001

Data Index: 1618671 (Python Code)

Max Activating Token Index: 1008

Text #6

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7668. Min Act: -0.0001

Data Index: 1549191 (Python Code)

Max Activating Token Index: 344

Text #7

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8072. Min Act: -0.0001

Data Index: 234128 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7823. Min Act: -0.0001

Data Index: 1114549 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7425. Min Act: -0.0001

Data Index: 840224 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7713. Min Act: -0.0001

Data Index: 427800 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7217. Min Act: -0.0001

Data Index: 735643 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7326. Min Act: -0.0001

Data Index: 1290174 (C4 (Web Text))

Max Activating Token Index: 186

Text #13

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.6407. Min Act: -0.0001

Data Index: 307517 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7394. Min Act: -0.0001

Data Index: 160577 (C4 (Web Text))

Max Activating Token Index: 1001

Text #15

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7172. Min Act: -0.0001

Data Index: 830979 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7366. Min Act: -0.0001

Data Index: 1504046 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7119. Min Act: -0.0001

Data Index: 1434350 (Python Code)

Max Activating Token Index: 972

Text #18

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1633560 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1084218 (C4 (Web Text))

Max Activating Token Index: 411