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

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

Neuron 2521 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2075. Min Range: -5.2075

Max Act: 5.2075. Min Act: -0.0000

Data Index: 603138 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 5.2075. Min Range: -5.2075

Max Act: 4.7631. Min Act: -0.0000

Data Index: 1197088 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.8081. Min Act: -0.0000

Data Index: 1356172 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.6124. Min Act: -0.0000

Data Index: 214035 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.5368. Min Act: -0.0000

Data Index: 229500 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.3281. Min Act: -0.0000

Data Index: 1189340 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.5293. Min Act: -0.0000

Data Index: 353657 (C4 (Web Text))

Max Activating Token Index: 162

Text #7

Max Range: 5.2075. Min Range: -5.2075

Max Act: 4.0898. Min Act: -0.0000

Data Index: 673680 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.4139. Min Act: -0.0000

Data Index: 306132 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.4192. Min Act: -0.0000

Data Index: 424766 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.9211. Min Act: -0.0000

Data Index: 479366 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.2422. Min Act: -0.0000

Data Index: 451354 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.4933. Min Act: -0.0000

Data Index: 669703 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.1862. Min Act: -0.0000

Data Index: 898258 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 5.2075. Min Range: -5.2075

Max Act: 3.5420. Min Act: -0.0000

Data Index: 929572 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.8250. Min Act: -0.0000

Data Index: 116477 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.8204. Min Act: -0.0000

Data Index: 348083 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.8950. Min Act: -0.0000

Data Index: 347470 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.7465. Min Act: -0.0000

Data Index: 202130 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 5.2075. Min Range: -5.2075

Max Act: 2.7136. Min Act: -0.0000

Data Index: 1357714 (C4 (Web Text))

Max Activating Token Index: 464