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

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

Neuron 2484 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3689. Min Act: -0.0001

Data Index: 1220192 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.3176. Min Act: -0.0000

Data Index: 436286 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2870. Min Act: -0.0000

Data Index: 470698 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2818. Min Act: -0.0000

Data Index: 351449 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2791. Min Act: -0.0000

Data Index: 807214 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2708. Min Act: -0.0000

Data Index: 133621 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2763. Min Act: -0.0000

Data Index: 931151 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2425. Min Act: -0.0000

Data Index: 717637 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2731. Min Act: -0.0000

Data Index: 462236 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1289899 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1128445 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2464. Min Act: -0.0000

Data Index: 544270 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2598. Min Act: -0.0000

Data Index: 862066 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2364. Min Act: -0.0000

Data Index: 1350101 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2526. Min Act: -0.0000

Data Index: 304845 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2599. Min Act: -0.0000

Data Index: 152158 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1003565 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2414. Min Act: -0.0000

Data Index: 225773 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1331534 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.3689. Min Range: -0.3689

Max Act: 0.2403. Min Act: -0.0000

Data Index: 912749 (C4 (Web Text))

Max Activating Token Index: 693