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

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

Neuron 2385 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4196. Min Act: -0.0003

Data Index: 1415588 (Python Code)

Max Activating Token Index: 688

Text #1

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4219. Min Act: -0.0003

Data Index: 1417071 (Python Code)

Max Activating Token Index: 630

Text #2

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4423. Min Act: -0.0003

Data Index: 1497790 (Python Code)

Max Activating Token Index: 504

Text #3

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4250. Min Act: -0.0003

Data Index: 1414950 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4143. Min Act: -0.0003

Data Index: 1247004 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4166. Min Act: -0.0003

Data Index: 1554361 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4394. Min Act: -0.0003

Data Index: 1498142 (Python Code)

Max Activating Token Index: 836

Text #7

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3846. Min Act: -0.0003

Data Index: 1515489 (Python Code)

Max Activating Token Index: 299

Text #8

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3805. Min Act: -0.0003

Data Index: 1376366 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4172. Min Act: -0.0003

Data Index: 1553921 (Python Code)

Max Activating Token Index: 651

Text #10

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.4112. Min Act: -0.0003

Data Index: 594397 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3351. Min Act: -0.0003

Data Index: 1395517 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3681. Min Act: -0.0003

Data Index: 1373442 (Python Code)

Max Activating Token Index: 297

Text #13

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3904. Min Act: -0.0003

Data Index: 348874 (C4 (Web Text))

Max Activating Token Index: 13

Text #14

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3895. Min Act: -0.0003

Data Index: 1582665 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3538. Min Act: -0.0003

Data Index: 1029995 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3849. Min Act: -0.0003

Data Index: 1563614 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3531. Min Act: -0.0003

Data Index: 60271 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3488. Min Act: -0.0003

Data Index: 1410961 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 0.4423. Min Range: -0.4423

Max Act: 0.3600. Min Act: -0.0003

Data Index: 1261900 (C4 (Web Text))

Max Activating Token Index: 8