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

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

Neuron 4066 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3860. Min Act: -0.0000

Data Index: 465548 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3107. Min Act: -0.0000

Data Index: 425822 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2924. Min Act: -0.0001

Data Index: 841280 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3005. Min Act: -0.0000

Data Index: 1025732 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3013. Min Act: -0.0000

Data Index: 622596 (C4 (Web Text))

Max Activating Token Index: 760

Text #5

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.3049. Min Act: -0.0000

Data Index: 112825 (C4 (Web Text))

Max Activating Token Index: 566

Text #6

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2919. Min Act: -0.0000

Data Index: 721676 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2593. Min Act: -0.0000

Data Index: 373092 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2658. Min Act: -0.0000

Data Index: 689282 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2802. Min Act: -0.0001

Data Index: 623120 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2617. Min Act: -0.0000

Data Index: 1064996 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2412. Min Act: 0.0001

Data Index: 767854 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2322. Min Act: -0.0000

Data Index: 555141 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2534. Min Act: -0.0000

Data Index: 189635 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2454. Min Act: -0.0000

Data Index: 234247 (C4 (Web Text))

Max Activating Token Index: 950

Text #15

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2435. Min Act: -0.0000

Data Index: 441100 (C4 (Web Text))

Max Activating Token Index: 529

Text #16

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2433. Min Act: -0.0000

Data Index: 430923 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1217324 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2290. Min Act: -0.0000

Data Index: 571819 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.3860. Min Range: -0.3860

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1317421 (C4 (Web Text))

Max Activating Token Index: 480