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

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

Neuron 3429 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1005. Min Range: -1.1005

Max Act: 1.0729. Min Act: -0.0000

Data Index: 841331 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 1.1005. Min Range: -1.1005

Max Act: 1.1005. Min Act: -0.0000

Data Index: 362066 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 1.1005. Min Range: -1.1005

Max Act: 1.0452. Min Act: -0.0000

Data Index: 449271 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.9443. Min Act: -0.0000

Data Index: 14518 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.8662. Min Act: -0.0000

Data Index: 686922 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7975. Min Act: -0.0000

Data Index: 73617 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1348925 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1472790 (Python Code)

Max Activating Token Index: 637

Text #8

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7586. Min Act: -0.0000

Data Index: 949579 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1402341 (Python Code)

Max Activating Token Index: 825

Text #10

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7623. Min Act: -0.0000

Data Index: 962410 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6974. Min Act: -0.0000

Data Index: 329665 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6893. Min Act: -0.0000

Data Index: 1622053 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.7059. Min Act: -0.0000

Data Index: 33993 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1595781 (Python Code)

Max Activating Token Index: 227

Text #15

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1455615 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1191571 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6545. Min Act: -0.0000

Data Index: 1429291 (Python Code)

Max Activating Token Index: 359

Text #18

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1512984 (Python Code)

Max Activating Token Index: 572

Text #19

Max Range: 1.1005. Min Range: -1.1005

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1385624 (Python Code)

Max Activating Token Index: 401