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

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

Neuron 2258 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: 0.6727. Min Range: -0.6727

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1435708 (Python Code)

Max Activating Token Index: 295

Text #1

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.6434. Min Act: -0.0001

Data Index: 1399973 (Python Code)

Max Activating Token Index: 96

Text #2

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5651. Min Act: -0.0001

Data Index: 1384771 (Python Code)

Max Activating Token Index: 424

Text #3

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5426. Min Act: -0.0001

Data Index: 1580859 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5086. Min Act: -0.0001

Data Index: 1449627 (Python Code)

Max Activating Token Index: 319

Text #5

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5449. Min Act: -0.0001

Data Index: 1504231 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5466. Min Act: -0.0001

Data Index: 1367666 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5554. Min Act: -0.0001

Data Index: 1578617 (Python Code)

Max Activating Token Index: 281

Text #8

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5112. Min Act: -0.0001

Data Index: 1564889 (Python Code)

Max Activating Token Index: 597

Text #9

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5315. Min Act: -0.0001

Data Index: 1502241 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4922. Min Act: -0.0001

Data Index: 1407637 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5368. Min Act: -0.0001

Data Index: 1494723 (Python Code)

Max Activating Token Index: 668

Text #12

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4833. Min Act: -0.0000

Data Index: 1485495 (Python Code)

Max Activating Token Index: 226

Text #13

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4928. Min Act: -0.0001

Data Index: 1396695 (Python Code)

Max Activating Token Index: 293

Text #14

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1464330 (Python Code)

Max Activating Token Index: 381

Text #15

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1642192 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5120. Min Act: -0.0001

Data Index: 1630316 (Python Code)

Max Activating Token Index: 216

Text #17

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.5076. Min Act: -0.0001

Data Index: 1510121 (Python Code)

Max Activating Token Index: 77

Text #18

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1508608 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 0.6727. Min Range: -0.6727

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1544181 (Python Code)

Max Activating Token Index: 330