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

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

Neuron 2747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4611. Min Act: -0.0003

Data Index: 192062 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.4179. Min Act: -0.0003

Data Index: 1235833 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3905. Min Act: -0.0003

Data Index: 1086755 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3924. Min Act: -0.0003

Data Index: 1349119 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3381. Min Act: -0.0003

Data Index: 727153 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3454. Min Act: -0.0003

Data Index: 346259 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3571. Min Act: -0.0003

Data Index: 246698 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3087. Min Act: -0.0004

Data Index: 408577 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3522. Min Act: -0.0003

Data Index: 67701 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.2956. Min Act: -0.0003

Data Index: 428979 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3628. Min Act: -0.0003

Data Index: 432870 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3157. Min Act: -0.0003

Data Index: 1160679 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3507. Min Act: -0.0004

Data Index: 8682 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3365. Min Act: -0.0004

Data Index: 392339 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3496. Min Act: -0.0003

Data Index: 929692 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3697. Min Act: -0.0003

Data Index: 348674 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3307. Min Act: -0.0003

Data Index: 1297697 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3531. Min Act: -0.0003

Data Index: 401776 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3402. Min Act: -0.0003

Data Index: 1160472 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.4611. Min Range: -0.4611

Max Act: 0.3751. Min Act: -0.0003

Data Index: 655941 (C4 (Web Text))

Max Activating Token Index: 538