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

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

Neuron 1108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4803. Min Range: -7.4803

Max Act: 7.4803. Min Act: -0.0000

Data Index: 1325713 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 7.4803. Min Range: -7.4803

Max Act: 6.4110. Min Act: -0.0000

Data Index: 548543 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.9505. Min Act: -0.0000

Data Index: 972990 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.6969. Min Act: -0.0000

Data Index: 134298 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.8671. Min Act: -0.0000

Data Index: 1103784 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.4922. Min Act: -0.0000

Data Index: 1107086 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.6592. Min Act: -0.0000

Data Index: 423943 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.2851. Min Act: -0.0000

Data Index: 561801 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.4497. Min Act: -0.0000

Data Index: 1350268 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.3428. Min Act: -0.0000

Data Index: 845319 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.3485. Min Act: -0.0000

Data Index: 1117834 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.1157. Min Act: -0.0000

Data Index: 47127 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.1401. Min Act: -0.0000

Data Index: 1004549 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.0971. Min Act: -0.0000

Data Index: 952384 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.1927. Min Act: -0.0000

Data Index: 1124018 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 7.4803. Min Range: -7.4803

Max Act: 4.9936. Min Act: -0.0000

Data Index: 948355 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.2876. Min Act: -0.0000

Data Index: 860968 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.2197. Min Act: -0.0000

Data Index: 1230688 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 7.4803. Min Range: -7.4803

Max Act: 5.0222. Min Act: -0.0000

Data Index: 1247278 (C4 (Web Text))

Max Activating Token Index: 240

Text #19

Max Range: 7.4803. Min Range: -7.4803

Max Act: 4.4947. Min Act: -0.0000

Data Index: 554760 (C4 (Web Text))

Max Activating Token Index: 654