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

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

Neuron 3063 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.1328. Min Act: -0.0001

Data Index: 1256558 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.1185. Min Act: -0.0001

Data Index: 1435738 (Python Code)

Max Activating Token Index: 838

Text #2

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0405. Min Act: -0.0001

Data Index: 1452776 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0547. Min Act: -0.0001

Data Index: 375301 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9874. Min Act: -0.0001

Data Index: 756924 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.1594. Min Act: -0.0001

Data Index: 1415261 (Python Code)

Max Activating Token Index: 687

Text #6

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0854. Min Act: -0.0001

Data Index: 283342 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0840. Min Act: -0.0001

Data Index: 930861 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0950. Min Act: -0.0001

Data Index: 641976 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0641. Min Act: -0.0001

Data Index: 54616 (C4 (Web Text))

Max Activating Token Index: 978

Text #10

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9982. Min Act: -0.0001

Data Index: 561284 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0826. Min Act: -0.0001

Data Index: 786737 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0264. Min Act: -0.0001

Data Index: 871271 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1512646 (Python Code)

Max Activating Token Index: 1001

Text #14

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9415. Min Act: -0.0001

Data Index: 791079 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9263. Min Act: -0.0001

Data Index: 361626 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0140. Min Act: -0.0001

Data Index: 395969 (C4 (Web Text))

Max Activating Token Index: 802

Text #17

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9540. Min Act: -0.0001

Data Index: 456245 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.1594. Min Range: -1.1594

Max Act: 0.9959. Min Act: -0.0001

Data Index: 1026960 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 1.1594. Min Range: -1.1594

Max Act: 1.0522. Min Act: -0.0001

Data Index: 805119 (C4 (Web Text))

Max Activating Token Index: 989