Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4256 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3523. Min Act: -0.0000

Data Index: 1317637 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3125. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1011284 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3051. Min Act: -0.0000

Data Index: 203120 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3130. Min Act: -0.0000

Data Index: 313350 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2990. Min Act: -0.0000

Data Index: 825263 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2879. Min Act: -0.0000

Data Index: 935037 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.3060. Min Act: -0.0000

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2854. Min Act: -0.0000

Data Index: 153690 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2812. Min Act: -0.0000

Data Index: 569933 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2978. Min Act: -0.0000

Data Index: 106474 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2793. Min Act: -0.0000

Data Index: 619717 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1340377 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2651. Min Act: -0.0000

Data Index: 348685 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2708. Min Act: -0.0000

Data Index: 785155 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2368. Min Act: -0.0000

Data Index: 935340 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2287. Min Act: 0.0000

Data Index: 927186 (C4 (Web Text))

Max Activating Token Index: 141

Text #17

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2371. Min Act: -0.0000

Data Index: 147452 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1121270 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.3523. Min Range: -0.3523

Max Act: 0.2359. Min Act: -0.0000

Data Index: 609715 (C4 (Web Text))

Max Activating Token Index: 121