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

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

Neuron 1207 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.8933. Min Act: -0.0000

Data Index: 153416 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.8186. Min Act: -0.0000

Data Index: 278986 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1078302 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.8240. Min Act: -0.0000

Data Index: 385565 (C4 (Web Text))

Max Activating Token Index: 1011

Text #4

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1349499 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.7416. Min Act: -0.0000

Data Index: 243683 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.7836. Min Act: -0.0000

Data Index: 294140 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6933. Min Act: -0.0000

Data Index: 482893 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6866. Min Act: -0.0000

Data Index: 779445 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.7134. Min Act: -0.0000

Data Index: 697295 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6650. Min Act: -0.0000

Data Index: 1217357 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6608. Min Act: -0.0000

Data Index: 970829 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6938. Min Act: -0.0000

Data Index: 930270 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6602. Min Act: -0.0000

Data Index: 874278 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1082880 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6554. Min Act: -0.0000

Data Index: 294654 (C4 (Web Text))

Max Activating Token Index: 336

Text #16

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6311. Min Act: -0.0000

Data Index: 224320 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1262799 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1489118 (Python Code)

Max Activating Token Index: 363

Text #19

Max Range: 0.8933. Min Range: -0.8933

Max Act: 0.6546. Min Act: -0.0000

Data Index: 467422 (C4 (Web Text))

Max Activating Token Index: 896