Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4781 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1564895 (Python Code)

Max Activating Token Index: 216

Text #1

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1438240 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1406327 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1426187 (Python Code)

Max Activating Token Index: 336

Text #4

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1483185 (Python Code)

Max Activating Token Index: 296

Text #5

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1434688 (Python Code)

Max Activating Token Index: 143

Text #6

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4736. Min Act: -0.0000

Data Index: 1605993 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4483. Min Act: -0.0000

Data Index: 1485399 (Python Code)

Max Activating Token Index: 673

Text #8

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1505116 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4037. Min Act: -0.0000

Data Index: 1383289 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1454906 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4507. Min Act: -0.0000

Data Index: 1482524 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4103. Min Act: -0.0000

Data Index: 533484 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1430360 (Python Code)

Max Activating Token Index: 334

Text #14

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1583152 (Python Code)

Max Activating Token Index: 948

Text #15

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4073. Min Act: -0.0000

Data Index: 1487231 (Python Code)

Max Activating Token Index: 662

Text #16

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1273402 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3754. Min Act: -0.0000

Data Index: 1391576 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.3799. Min Act: -0.0000

Data Index: 1369984 (Python Code)

Max Activating Token Index: 96

Text #19

Max Range: 0.6347. Min Range: -0.6347

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1471902 (Python Code)

Max Activating Token Index: 120