Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2803 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.2543. Min Range: -2.2543

Max Act: 2.2543. Min Act: -0.0000

Data Index: 1376989 (Python Code)

Max Activating Token Index: 745

Text #1

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.9005. Min Act: -0.0000

Data Index: 1400637 (Python Code)

Max Activating Token Index: 173

Text #2

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.9163. Min Act: -0.0000

Data Index: 1578865 (Python Code)

Max Activating Token Index: 807

Text #3

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.9821. Min Act: -0.0000

Data Index: 1529203 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.8543. Min Act: -0.0000

Data Index: 1525522 (Python Code)

Max Activating Token Index: 617

Text #5

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.7129. Min Act: -0.0000

Data Index: 1611840 (Python Code)

Max Activating Token Index: 516

Text #6

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.6823. Min Act: -0.0000

Data Index: 1422918 (Python Code)

Max Activating Token Index: 643

Text #7

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.7003. Min Act: -0.0000

Data Index: 1147004 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4962. Min Act: -0.0000

Data Index: 885492 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.5362. Min Act: -0.0000

Data Index: 1502554 (Python Code)

Max Activating Token Index: 791

Text #10

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1581897 (Python Code)

Max Activating Token Index: 749

Text #11

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.5427. Min Act: -0.0000

Data Index: 1202377 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.5196. Min Act: -0.0000

Data Index: 1588081 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1410520 (Python Code)

Max Activating Token Index: 664

Text #14

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.5462. Min Act: -0.0000

Data Index: 1543968 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1444491 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4080. Min Act: -0.0000

Data Index: 61875 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4243. Min Act: -0.0000

Data Index: 603981 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1470455 (Python Code)

Max Activating Token Index: 315

Text #19

Max Range: 2.2543. Min Range: -2.2543

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1556740 (Python Code)

Max Activating Token Index: 291