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

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

Neuron 2321 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: 2.1206. Min Range: -2.1206

Max Act: 2.0543. Min Act: -0.0000

Data Index: 1132626 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.1206. Min Range: -2.1206

Max Act: 2.1206. Min Act: -0.0000

Data Index: 506239 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.9780. Min Act: -0.0000

Data Index: 912127 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 2.1206. Min Range: -2.1206

Max Act: 2.0775. Min Act: -0.0000

Data Index: 340840 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.9104. Min Act: -0.0000

Data Index: 269501 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.9982. Min Act: -0.0000

Data Index: 832388 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.9026. Min Act: -0.0000

Data Index: 919354 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8769. Min Act: -0.0000

Data Index: 1332952 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8671. Min Act: -0.0000

Data Index: 648930 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8589. Min Act: -0.0000

Data Index: 1101917 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8305. Min Act: -0.0000

Data Index: 1082577 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.7696. Min Act: -0.0000

Data Index: 829156 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8585. Min Act: -0.0000

Data Index: 935679 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.8359. Min Act: -0.0000

Data Index: 350580 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.5501. Min Act: -0.0000

Data Index: 388304 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.5242. Min Act: -0.0000

Data Index: 248937 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.5855. Min Act: -0.0000

Data Index: 303311 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.6198. Min Act: -0.0000

Data Index: 372259 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.4930. Min Act: -0.0000

Data Index: 433903 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 2.1206. Min Range: -2.1206

Max Act: 1.4872. Min Act: -0.0000

Data Index: 1262317 (C4 (Web Text))

Max Activating Token Index: 882