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

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

Neuron 4455 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: 0.3081. Min Range: -0.3081

Max Act: 0.3081. Min Act: -0.0000

Data Index: 448036 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2435. Min Act: -0.0000

Data Index: 53502 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.2094. Min Act: -0.0000

Data Index: 91923 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1981. Min Act: -0.0000

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1975. Min Act: -0.0000

Data Index: 535943 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1673. Min Act: -0.0000

Data Index: 360587 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1260738 (C4 (Web Text))

Max Activating Token Index: 808

Text #7

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1898. Min Act: -0.0000

Data Index: 228919 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1453975 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1648. Min Act: -0.0000

Data Index: 12750 (C4 (Web Text))

Max Activating Token Index: 583

Text #10

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1173070 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1683. Min Act: -0.0000

Data Index: 972599 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1669. Min Act: -0.0000

Data Index: 915355 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1648. Min Act: -0.0000

Data Index: 1284135 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1715. Min Act: -0.0000

Data Index: 745881 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1567. Min Act: -0.0000

Data Index: 1277629 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1532. Min Act: -0.0000

Data Index: 526857 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1455. Min Act: -0.0000

Data Index: 627187 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1630. Min Act: -0.0000

Data Index: 949378 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.3081. Min Range: -0.3081

Max Act: 0.1549. Min Act: -0.0000

Data Index: 798155 (C4 (Web Text))

Max Activating Token Index: 324