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

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

Neuron 4396 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0243. Min Range: -4.0243

Max Act: 4.0243. Min Act: -0.0000

Data Index: 30776 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.9472. Min Act: -0.0000

Data Index: 414786 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.5609. Min Act: -0.0000

Data Index: 333705 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.2456. Min Act: -0.0000

Data Index: 23232 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.1546. Min Act: -0.0000

Data Index: 1063454 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.1547. Min Act: -0.0000

Data Index: 578651 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.9732. Min Act: -0.0000

Data Index: 848330 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.0823. Min Act: -0.0000

Data Index: 1039958 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.9215. Min Act: -0.0000

Data Index: 371935 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.0486. Min Act: -0.0000

Data Index: 607238 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 4.0243. Min Range: -4.0243

Max Act: 3.0585. Min Act: -0.0000

Data Index: 562417 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8914. Min Act: -0.0000

Data Index: 187988 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8992. Min Act: -0.0000

Data Index: 1191531 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8818. Min Act: -0.0000

Data Index: 136365 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8805. Min Act: -0.0000

Data Index: 957303 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.6969. Min Act: -0.0000

Data Index: 138215 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8466. Min Act: -0.0000

Data Index: 496728 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8150. Min Act: -0.0000

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.8125. Min Act: -0.0000

Data Index: 867962 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 4.0243. Min Range: -4.0243

Max Act: 2.7743. Min Act: -0.0000

Data Index: 152504 (C4 (Web Text))

Max Activating Token Index: 381