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

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

Neuron 2084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7669. Min Act: -0.0001

Data Index: 145851 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7888. Min Act: -0.0001

Data Index: 1149737 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7320. Min Act: -0.0001

Data Index: 1147658 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1142177 (C4 (Web Text))

Max Activating Token Index: 415

Text #4

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7025. Min Act: -0.0001

Data Index: 381343 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1062725 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.7188. Min Act: -0.0001

Data Index: 261122 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6731. Min Act: -0.0001

Data Index: 963786 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6808. Min Act: -0.0001

Data Index: 45365 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6558. Min Act: -0.0001

Data Index: 788491 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6878. Min Act: -0.0000

Data Index: 734685 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6449. Min Act: -0.0001

Data Index: 705580 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6409. Min Act: -0.0001

Data Index: 1116490 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6147. Min Act: -0.0001

Data Index: 942219 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6477. Min Act: -0.0001

Data Index: 852531 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6084. Min Act: -0.0001

Data Index: 1145614 (C4 (Web Text))

Max Activating Token Index: 912

Text #16

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6386. Min Act: -0.0001

Data Index: 1156575 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6076. Min Act: -0.0001

Data Index: 1201426 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6221. Min Act: -0.0001

Data Index: 495002 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.7888. Min Range: -0.7888

Max Act: 0.6218. Min Act: -0.0001

Data Index: 902841 (C4 (Web Text))

Max Activating Token Index: 974