Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 3001 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2441. Min Act: -0.0001

Data Index: 768790 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2283. Min Act: -0.0001

Data Index: 424226 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2417. Min Act: -0.0001

Data Index: 746461 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1161377 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2297. Min Act: -0.0001

Data Index: 297847 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1963. Min Act: -0.0001

Data Index: 644822 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2060. Min Act: -0.0001

Data Index: 515253 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2134. Min Act: -0.0001

Data Index: 263119 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1894. Min Act: -0.0001

Data Index: 36450 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2095. Min Act: -0.0001

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1924. Min Act: -0.0001

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.2049. Min Act: -0.0001

Data Index: 957397 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1107301 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1853. Min Act: -0.0001

Data Index: 476620 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1776. Min Act: -0.0001

Data Index: 700399 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1194625 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1752. Min Act: -0.0001

Data Index: 53690 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1868. Min Act: -0.0001

Data Index: 509089 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1793. Min Act: -0.0001

Data Index: 254853 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.2441. Min Range: -0.2441

Max Act: 0.1862. Min Act: -0.0001

Data Index: 244384 (C4 (Web Text))

Max Activating Token Index: 261