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

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

Neuron 3226 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.6462. Min Act: -0.0000

Data Index: 999059 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.1181. Min Act: -0.0001

Data Index: 172062 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.7232. Min Act: -0.0000

Data Index: 536609 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.5711. Min Act: -0.0001

Data Index: 138563 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.0596. Min Act: -0.0001

Data Index: 298533 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7999. Min Act: -0.0000

Data Index: 1171454 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.8737. Min Act: -0.0001

Data Index: 23089 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.6949. Min Act: -0.0001

Data Index: 149791 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.8428. Min Act: -0.0000

Data Index: 465059 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.9404. Min Act: -0.0000

Data Index: 946929 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7467. Min Act: -0.0001

Data Index: 902577 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7867. Min Act: -0.0001

Data Index: 496507 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7939. Min Act: -0.0001

Data Index: 445587 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.6476. Min Act: -0.0000

Data Index: 880086 (C4 (Web Text))

Max Activating Token Index: 190

Text #14

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7460. Min Act: -0.0000

Data Index: 438489 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 2.7232. Min Range: -2.7232

Max Act: 2.1479. Min Act: -0.0001

Data Index: 204612 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1358788 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1109884 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.6154. Min Act: -0.0000

Data Index: 195788 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 2.7232. Min Range: -2.7232

Max Act: 1.7847. Min Act: -0.0000

Data Index: 207386 (C4 (Web Text))

Max Activating Token Index: 103