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

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

Neuron 524 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.7839. Min Act: -0.0001

Data Index: 1065975 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.5765. Min Act: -0.0001

Data Index: 1200601 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.6443. Min Act: -0.0001

Data Index: 840524 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.5333. Min Act: -0.0001

Data Index: 1357771 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3466. Min Act: -0.0001

Data Index: 247939 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3906. Min Act: -0.0001

Data Index: 1144830 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3615. Min Act: -0.0001

Data Index: 898084 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3532. Min Act: -0.0001

Data Index: 384090 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3756. Min Act: -0.0001

Data Index: 1230056 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2552. Min Act: -0.0001

Data Index: 539948 (C4 (Web Text))

Max Activating Token Index: 579

Text #10

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.3171. Min Act: -0.0001

Data Index: 1346071 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2224. Min Act: -0.0001

Data Index: 1128197 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2529. Min Act: -0.0001

Data Index: 1136808 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.1947. Min Act: -0.0001

Data Index: 519551 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2944. Min Act: -0.0001

Data Index: 682421 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2686. Min Act: -0.0001

Data Index: 135166 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2512. Min Act: -0.0001

Data Index: 34187 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.1838. Min Act: -0.0001

Data Index: 281683 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 1.7839. Min Range: -1.7839

Max Act: 1.2107. Min Act: -0.0001

Data Index: 176221 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 1.7839. Min Range: -1.7839

Max Act: 0.8595. Min Act: -0.0001

Data Index: 667040 (C4 (Web Text))

Max Activating Token Index: 125