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

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

Neuron 2889 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.4605. Min Act: -0.0001

Data Index: 486540 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.3250. Min Act: -0.0001

Data Index: 236274 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0968. Min Act: -0.0001

Data Index: 1483334 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.2032. Min Act: -0.0001

Data Index: 364909 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.2064. Min Act: -0.0001

Data Index: 363181 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.1631. Min Act: -0.0001

Data Index: 197543 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.1223. Min Act: -0.0001

Data Index: 148131 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.1149. Min Act: -0.0001

Data Index: 414195 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1629758 (Python Code)

Max Activating Token Index: 88

Text #9

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0712. Min Act: -0.0001

Data Index: 361621 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0960. Min Act: -0.0001

Data Index: 1023916 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9639. Min Act: -0.0001

Data Index: 159988 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9864. Min Act: -0.0001

Data Index: 1303306 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0719. Min Act: -0.0001

Data Index: 94416 (C4 (Web Text))

Max Activating Token Index: 871

Text #14

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.1351. Min Act: -0.0001

Data Index: 403289 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9983. Min Act: -0.0001

Data Index: 471919 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9995. Min Act: -0.0001

Data Index: 247744 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.4605. Min Range: -1.4605

Max Act: 1.0496. Min Act: -0.0001

Data Index: 1336403 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.9646. Min Act: -0.0001

Data Index: 788447 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 1.4605. Min Range: -1.4605

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1434654 (Python Code)

Max Activating Token Index: 312