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

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

Neuron 3208 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.6564. Min Act: -0.0000

Data Index: 437328 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.7808. Min Act: -0.0000

Data Index: 684429 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.8217. Min Act: -0.0000

Data Index: 1227142 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.5868. Min Act: -0.0000

Data Index: 809824 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.8982. Min Act: -0.0000

Data Index: 741747 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.7113. Min Act: -0.0000

Data Index: 225812 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.8369. Min Act: -0.0000

Data Index: 908934 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.8516. Min Act: -0.0000

Data Index: 1005353 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.6498. Min Act: -0.0000

Data Index: 259020 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.6268. Min Act: -0.0000

Data Index: 1207034 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.5817. Min Act: -0.0000

Data Index: 967394 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.5556. Min Act: -0.0000

Data Index: 1121963 (C4 (Web Text))

Max Activating Token Index: 93

Text #12

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.3783. Min Act: -0.0000

Data Index: 381258 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.3970. Min Act: -0.0000

Data Index: 632324 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.5538. Min Act: -0.0000

Data Index: 1206773 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.8584. Min Act: -0.0000

Data Index: 288218 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.4869. Min Act: -0.0000

Data Index: 72728 (C4 (Web Text))

Max Activating Token Index: 488

Text #17

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.4622. Min Act: -0.0000

Data Index: 366204 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.4858. Min Act: -0.0000

Data Index: 246368 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 4.8982. Min Range: -4.8982

Max Act: 4.4425. Min Act: -0.0000

Data Index: 1175074 (C4 (Web Text))

Max Activating Token Index: 624