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

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

Neuron 3024 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: 0.4109. Min Range: -0.4109

Max Act: 0.3671. Min Act: -0.0001

Data Index: 46541 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3950. Min Act: -0.0001

Data Index: 503394 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.4109. Min Act: -0.0001

Data Index: 1178385 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3706. Min Act: -0.0001

Data Index: 829441 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3720. Min Act: -0.0001

Data Index: 1223402 (C4 (Web Text))

Max Activating Token Index: 980

Text #5

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1353781 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3588. Min Act: -0.0001

Data Index: 771779 (C4 (Web Text))

Max Activating Token Index: 211

Text #7

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3354. Min Act: -0.0001

Data Index: 162072 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3285. Min Act: -0.0001

Data Index: 514806 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3369. Min Act: -0.0001

Data Index: 357250 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3459. Min Act: -0.0001

Data Index: 408850 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1155571 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3269. Min Act: -0.0001

Data Index: 637716 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3593. Min Act: -0.0001

Data Index: 600016 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3407. Min Act: -0.0001

Data Index: 1284188 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3180. Min Act: -0.0001

Data Index: 453347 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3399. Min Act: -0.0001

Data Index: 1270109 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3156. Min Act: -0.0001

Data Index: 1113834 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3254. Min Act: -0.0001

Data Index: 741416 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.4109. Min Range: -0.4109

Max Act: 0.3221. Min Act: -0.0001

Data Index: 1182741 (C4 (Web Text))

Max Activating Token Index: 98