Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0006

Data Index: 94018 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0617. Min Act: -0.0006

Data Index: 1195538 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0499. Min Act: -0.0005

Data Index: 826171 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0467. Min Act: -0.0005

Data Index: 133554 (C4 (Web Text))

Max Activating Token Index: 529

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0483. Min Act: -0.0006

Data Index: 826207 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0472. Min Act: -0.0005

Data Index: 162920 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0458. Min Act: -0.0006

Data Index: 543894 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0456. Min Act: -0.0005

Data Index: 1245434 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0460. Min Act: -0.0006

Data Index: 855730 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0440. Min Act: -0.0006

Data Index: 1172501 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0447. Min Act: -0.0005

Data Index: 1077243 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0435. Min Act: -0.0006

Data Index: 299760 (C4 (Web Text))

Max Activating Token Index: 107

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0442. Min Act: -0.0006

Data Index: 894960 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0435. Min Act: -0.0006

Data Index: 1154936 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0442. Min Act: -0.0006

Data Index: 679052 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0422. Min Act: -0.0006

Data Index: 399933 (C4 (Web Text))

Max Activating Token Index: 409

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0421. Min Act: -0.0005

Data Index: 211996 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0445. Min Act: -0.0006

Data Index: 285095 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0420. Min Act: -0.0006

Data Index: 34135 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0429. Min Act: -0.0006

Data Index: 754265 (C4 (Web Text))

Max Activating Token Index: 784