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

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

Neuron 2508 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1604867 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.8772. Min Act: -0.0000

Data Index: 1595086 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1572040 (Python Code)

Max Activating Token Index: 506

Text #3

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7268. Min Act: -0.0000

Data Index: 33517 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7031. Min Act: -0.0000

Data Index: 1531087 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1387995 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1608259 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1380031 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1633567 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1609923 (Python Code)

Max Activating Token Index: 57

Text #10

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1509737 (Python Code)

Max Activating Token Index: 397

Text #11

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1459577 (Python Code)

Max Activating Token Index: 873

Text #12

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1509286 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5509. Min Act: -0.0000

Data Index: 1422496 (Python Code)

Max Activating Token Index: 458

Text #14

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5837. Min Act: -0.0000

Data Index: 1473448 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5792. Min Act: -0.0000

Data Index: 818266 (C4 (Web Text))

Max Activating Token Index: 935

Text #16

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5652. Min Act: -0.0000

Data Index: 932006 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1316956 (C4 (Web Text))

Max Activating Token Index: 758

Text #18

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1613993 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 0.9835. Min Range: -0.9835

Max Act: 0.5710. Min Act: -0.0000

Data Index: 1652685 (Python Code)

Max Activating Token Index: 351