Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1979 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3849. Min Act: -0.0000

Data Index: 774323 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.3205. Min Act: -0.0001

Data Index: 495418 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2930. Min Act: -0.0001

Data Index: 410482 (C4 (Web Text))

Max Activating Token Index: 1015

Text #3

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2668. Min Act: -0.0001

Data Index: 381206 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1123375 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2666. Min Act: -0.0001

Data Index: 805978 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2683. Min Act: -0.0001

Data Index: 1342260 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2638. Min Act: -0.0001

Data Index: 224715 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2495. Min Act: -0.0001

Data Index: 582172 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2339. Min Act: -0.0001

Data Index: 50457 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2375. Min Act: -0.0001

Data Index: 393482 (C4 (Web Text))

Max Activating Token Index: 703

Text #11

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2367. Min Act: -0.0001

Data Index: 603653 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2463. Min Act: -0.0001

Data Index: 1036238 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2326. Min Act: -0.0001

Data Index: 464258 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2135. Min Act: -0.0001

Data Index: 339266 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2315. Min Act: -0.0001

Data Index: 965942 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1325864 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2310. Min Act: -0.0001

Data Index: 105113 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2263. Min Act: -0.0001

Data Index: 751211 (C4 (Web Text))

Max Activating Token Index: 843

Text #19

Max Range: 0.3849. Min Range: -0.3849

Max Act: 0.2288. Min Act: -0.0000

Data Index: 321414 (C4 (Web Text))

Max Activating Token Index: 228