Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2236 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.1401. Min Range: -8.1401

Max Act: 8.1401. Min Act: -0.0000

Data Index: 1023969 (C4 (Web Text))

Max Activating Token Index: 548

Text #1

Max Range: 8.1401. Min Range: -8.1401

Max Act: 6.6631. Min Act: -0.0000

Data Index: 498797 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.9641. Min Act: -0.0000

Data Index: 404422 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.7268. Min Act: -0.0000

Data Index: 429299 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.8938. Min Act: -0.0000

Data Index: 1273274 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.8880. Min Act: -0.0000

Data Index: 236327 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.6172. Min Act: -0.0000

Data Index: 238417 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.6022. Min Act: -0.0000

Data Index: 49712 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.3863. Min Act: -0.0000

Data Index: 322118 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.2326. Min Act: -0.0000

Data Index: 1277122 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.5076. Min Act: -0.0000

Data Index: 1204867 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.3136. Min Act: -0.0000

Data Index: 920366 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.6762. Min Act: -0.0000

Data Index: 1062818 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.8124. Min Act: -0.0000

Data Index: 1051898 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.4312. Min Act: -0.0000

Data Index: 837155 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.4318. Min Act: -0.0000

Data Index: 50718 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.4155. Min Act: -0.0000

Data Index: 846306 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.2199. Min Act: -0.0000

Data Index: 813093 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 8.1401. Min Range: -8.1401

Max Act: 4.9983. Min Act: -0.0000

Data Index: 257359 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 8.1401. Min Range: -8.1401

Max Act: 5.3500. Min Act: -0.0000

Data Index: 401383 (C4 (Web Text))

Max Activating Token Index: 675