Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2147 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0874. Min Range: -1.0874

Max Act: 1.0874. Min Act: -0.0001

Data Index: 702253 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7954. Min Act: -0.0001

Data Index: 431148 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.8277. Min Act: -0.0001

Data Index: 457622 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.8389. Min Act: -0.0001

Data Index: 1193065 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.8131. Min Act: -0.0001

Data Index: 1308252 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7655. Min Act: -0.0001

Data Index: 721413 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7366. Min Act: -0.0001

Data Index: 747278 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.8039. Min Act: -0.0001

Data Index: 87337 (C4 (Web Text))

Max Activating Token Index: 362

Text #8

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7650. Min Act: -0.0001

Data Index: 1009880 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7559. Min Act: -0.0001

Data Index: 737388 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.8040. Min Act: -0.0001

Data Index: 66758 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7759. Min Act: -0.0001

Data Index: 248896 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7761. Min Act: -0.0001

Data Index: 736256 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7984. Min Act: -0.0001

Data Index: 421676 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7456. Min Act: -0.0001

Data Index: 675369 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7991. Min Act: -0.0001

Data Index: 1241507 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7231. Min Act: -0.0001

Data Index: 708651 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.7189. Min Act: -0.0001

Data Index: 360991 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.6901. Min Act: -0.0001

Data Index: 568603 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 1.0874. Min Range: -1.0874

Max Act: 0.6879. Min Act: -0.0001

Data Index: 1288378 (C4 (Web Text))

Max Activating Token Index: 706