Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4210 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.4408. Min Act: -0.0000

Data Index: 148062 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.6240. Min Act: -0.0000

Data Index: 858080 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.3963. Min Act: -0.0000

Data Index: 948618 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.4098. Min Act: -0.0000

Data Index: 1295395 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2778. Min Act: -0.0000

Data Index: 666898 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2456. Min Act: -0.0000

Data Index: 95201 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1436. Min Act: -0.0000

Data Index: 884148 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2892. Min Act: -0.0000

Data Index: 760146 (C4 (Web Text))

Max Activating Token Index: 991

Text #8

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2109. Min Act: -0.0000

Data Index: 963652 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.2109. Min Act: -0.0000

Data Index: 634928 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1950. Min Act: -0.0000

Data Index: 881890 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1136. Min Act: -0.0000

Data Index: 467490 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1918. Min Act: -0.0000

Data Index: 782377 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1618. Min Act: -0.0000

Data Index: 197335 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1161966 (C4 (Web Text))

Max Activating Token Index: 986

Text #15

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1523. Min Act: -0.0000

Data Index: 560923 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1413. Min Act: -0.0000

Data Index: 1296468 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1332. Min Act: -0.0000

Data Index: 1169429 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.1185. Min Act: -0.0000

Data Index: 716586 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 1.6240. Min Range: -1.6240

Max Act: 1.0317. Min Act: -0.0000

Data Index: 1196122 (C4 (Web Text))

Max Activating Token Index: 226