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

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

Neuron 2818 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: 0.4074. Min Range: -0.4074

Max Act: 0.4039. Min Act: -0.0000

Data Index: 637075 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1500629 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3720. Min Act: -0.0000

Data Index: 636214 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1417940 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1616828 (Python Code)

Max Activating Token Index: 265

Text #5

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3321. Min Act: -0.0000

Data Index: 837541 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3453. Min Act: -0.0000

Data Index: 840860 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3165. Min Act: -0.0000

Data Index: 688929 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1441833 (Python Code)

Max Activating Token Index: 483

Text #9

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3360. Min Act: -0.0000

Data Index: 1302821 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1255753 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1383044 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1505445 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1316295 (C4 (Web Text))

Max Activating Token Index: 506

Text #14

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.3088. Min Act: -0.0000

Data Index: 1152516 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2744. Min Act: -0.0000

Data Index: 343900 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2929. Min Act: -0.0000

Data Index: 894724 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1005521 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2892. Min Act: -0.0000

Data Index: 569996 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.4074. Min Range: -0.4074

Max Act: 0.2673. Min Act: 0.0000

Data Index: 22568 (C4 (Web Text))

Max Activating Token Index: 307