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

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

Neuron 904 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: 3.2040. Min Range: -3.2040

Max Act: 3.2040. Min Act: -0.0001

Data Index: 1207112 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 3.2040. Min Range: -3.2040

Max Act: 3.1375. Min Act: -0.0001

Data Index: 1066417 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6704. Min Act: -0.0001

Data Index: 172680 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6694. Min Act: -0.0001

Data Index: 916848 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.7706. Min Act: -0.0001

Data Index: 871567 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6110. Min Act: -0.0001

Data Index: 913382 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.8561. Min Act: -0.0001

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.5493. Min Act: -0.0001

Data Index: 517162 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.5234. Min Act: -0.0001

Data Index: 1243359 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.7533. Min Act: -0.0001

Data Index: 615498 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.5604. Min Act: -0.0001

Data Index: 847029 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.3850. Min Act: -0.0001

Data Index: 146209 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.6200. Min Act: -0.0001

Data Index: 176269 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.3135. Min Act: -0.0001

Data Index: 626949 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.2952. Min Act: -0.0001

Data Index: 1081397 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.3436. Min Act: -0.0001

Data Index: 734735 (C4 (Web Text))

Max Activating Token Index: 896

Text #16

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.2072. Min Act: -0.0001

Data Index: 722012 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.2833. Min Act: -0.0001

Data Index: 402020 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 3.2040. Min Range: -3.2040

Max Act: 2.0889. Min Act: -0.0001

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 3.2040. Min Range: -3.2040

Max Act: 1.9532. Min Act: -0.0001

Data Index: 455190 (C4 (Web Text))

Max Activating Token Index: 292