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

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

Neuron 2970 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6959. Min Act: -0.0001

Data Index: 1633622 (Python Code)

Max Activating Token Index: 980

Text #1

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6493. Min Act: -0.0001

Data Index: 1566676 (Python Code)

Max Activating Token Index: 1022

Text #2

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5987. Min Act: -0.0001

Data Index: 1396961 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6425. Min Act: -0.0001

Data Index: 1569171 (Python Code)

Max Activating Token Index: 671

Text #4

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1425305 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5961. Min Act: -0.0001

Data Index: 1388017 (Python Code)

Max Activating Token Index: 55

Text #6

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6024. Min Act: -0.0001

Data Index: 1378584 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.6130. Min Act: -0.0001

Data Index: 1639432 (Python Code)

Max Activating Token Index: 856

Text #8

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5886. Min Act: -0.0001

Data Index: 1366336 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5999. Min Act: -0.0001

Data Index: 1644076 (Python Code)

Max Activating Token Index: 352

Text #10

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5681. Min Act: -0.0001

Data Index: 1555342 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5699. Min Act: -0.0001

Data Index: 1534291 (Python Code)

Max Activating Token Index: 645

Text #12

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5644. Min Act: -0.0002

Data Index: 186036 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5886. Min Act: -0.0001

Data Index: 1421225 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5693. Min Act: -0.0001

Data Index: 1652987 (Python Code)

Max Activating Token Index: 855

Text #15

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5714. Min Act: -0.0001

Data Index: 1383995 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1420240 (Python Code)

Max Activating Token Index: 159

Text #17

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5845. Min Act: -0.0001

Data Index: 1505678 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.4881. Min Act: -0.0002

Data Index: 18824 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.6959. Min Range: -0.6959

Max Act: 0.5382. Min Act: -0.0001

Data Index: 1403744 (Python Code)

Max Activating Token Index: 47