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

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

Neuron 2195 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3969. Min Range: -5.3969

Max Act: 5.3969. Min Act: -0.0000

Data Index: 109695 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.8996. Min Act: -0.0000

Data Index: 423907 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.6087. Min Act: -0.0000

Data Index: 1107575 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.5190. Min Act: -0.0000

Data Index: 49411 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.3004. Min Act: -0.0000

Data Index: 336501 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.6203. Min Act: -0.0000

Data Index: 1041109 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.2219. Min Act: -0.0000

Data Index: 474185 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.4730. Min Act: -0.0000

Data Index: 811902 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.2988. Min Act: -0.0000

Data Index: 503791 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.4627. Min Act: -0.0000

Data Index: 1083283 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.0929. Min Act: -0.0000

Data Index: 1103161 (C4 (Web Text))

Max Activating Token Index: 348

Text #11

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.2474. Min Act: -0.0000

Data Index: 799452 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.2148. Min Act: -0.0000

Data Index: 263491 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.3627. Min Act: -0.0000

Data Index: 727293 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.3189. Min Act: -0.0000

Data Index: 935237 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.0935. Min Act: -0.0000

Data Index: 943429 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.0509. Min Act: -0.0000

Data Index: 775956 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.0480. Min Act: -0.0000

Data Index: 1156317 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 5.3969. Min Range: -5.3969

Max Act: 4.0001. Min Act: -0.0000

Data Index: 877228 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 5.3969. Min Range: -5.3969

Max Act: 3.7769. Min Act: -0.0000

Data Index: 1136682 (C4 (Web Text))

Max Activating Token Index: 65