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

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

Neuron 3133 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.8045. Min Act: -0.0000

Data Index: 1504718 (Python Code)

Max Activating Token Index: 294

Text #1

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.7216. Min Act: -0.0000

Data Index: 1385044 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1627273 (Python Code)

Max Activating Token Index: 917

Text #3

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1381050 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4360. Min Act: -0.0000

Data Index: 1521447 (Python Code)

Max Activating Token Index: 421

Text #5

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1565527 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4320. Min Act: -0.0000

Data Index: 859559 (C4 (Web Text))

Max Activating Token Index: 452

Text #7

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.4120. Min Act: -0.0000

Data Index: 1465616 (Python Code)

Max Activating Token Index: 755

Text #8

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3922. Min Act: -0.0000

Data Index: 864468 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3993. Min Act: -0.0000

Data Index: 1439934 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1445452 (Python Code)

Max Activating Token Index: 355

Text #11

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1418096 (Python Code)

Max Activating Token Index: 35

Text #12

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1397879 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3658. Min Act: -0.0000

Data Index: 939892 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1490832 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1616038 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3861. Min Act: -0.0000

Data Index: 978453 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1394514 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3461. Min Act: -0.0000

Data Index: 785727 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.8045. Min Range: -0.8045

Max Act: 0.3854. Min Act: -0.0000

Data Index: 429598 (C4 (Web Text))

Max Activating Token Index: 413