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

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

Neuron 558 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: 3.3687. Min Range: -3.3687

Max Act: 3.3687. Min Act: -0.0000

Data Index: 1015237 (C4 (Web Text))

Max Activating Token Index: 330

Text #1

Max Range: 3.3687. Min Range: -3.3687

Max Act: 3.1012. Min Act: -0.0000

Data Index: 117046 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.9535. Min Act: -0.0000

Data Index: 854019 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.8450. Min Act: -0.0000

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.4559. Min Act: -0.0000

Data Index: 23407 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.6978. Min Act: -0.0000

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.2150. Min Act: -0.0000

Data Index: 1168214 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.1830. Min Act: -0.0000

Data Index: 576635 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.5093. Min Act: -0.0000

Data Index: 726499 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.2649. Min Act: -0.0000

Data Index: 810263 (C4 (Web Text))

Max Activating Token Index: 465

Text #10

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.0228. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.1057. Min Act: -0.0000

Data Index: 304355 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.0053. Min Act: -0.0000

Data Index: 435135 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 3.3687. Min Range: -3.3687

Max Act: 1.9274. Min Act: -0.0000

Data Index: 430984 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 3.3687. Min Range: -3.3687

Max Act: 1.9145. Min Act: -0.0000

Data Index: 1255043 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.1226. Min Act: -0.0000

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 3.3687. Min Range: -3.3687

Max Act: 1.9948. Min Act: -0.0001

Data Index: 1127166 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 3.3687. Min Range: -3.3687

Max Act: 1.9572. Min Act: -0.0001

Data Index: 686067 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 3.3687. Min Range: -3.3687

Max Act: 1.6401. Min Act: -0.0000

Data Index: 90901 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 3.3687. Min Range: -3.3687

Max Act: 2.0567. Min Act: -0.0000

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 315