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

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

Neuron 1965 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2791. Min Act: -0.0001

Data Index: 1284941 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2612. Min Act: -0.0001

Data Index: 428680 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2415. Min Act: -0.0001

Data Index: 1059015 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2425. Min Act: -0.0001

Data Index: 284809 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2486. Min Act: -0.0001

Data Index: 934 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2503. Min Act: -0.0001

Data Index: 1013577 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2396. Min Act: -0.0001

Data Index: 1228265 (C4 (Web Text))

Max Activating Token Index: 975

Text #7

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2359. Min Act: -0.0001

Data Index: 794706 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2321. Min Act: -0.0001

Data Index: 183206 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1057826 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2337. Min Act: -0.0001

Data Index: 740192 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2322. Min Act: -0.0001

Data Index: 985724 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2303. Min Act: -0.0001

Data Index: 614083 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2366. Min Act: -0.0001

Data Index: 813828 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2260. Min Act: -0.0001

Data Index: 245050 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2243. Min Act: -0.0001

Data Index: 1155709 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2183. Min Act: -0.0001

Data Index: 1228090 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2231. Min Act: -0.0001

Data Index: 904602 (C4 (Web Text))

Max Activating Token Index: 224

Text #18

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2068. Min Act: -0.0001

Data Index: 185659 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.2791. Min Range: -0.2791

Max Act: 0.2063. Min Act: -0.0001

Data Index: 456696 (C4 (Web Text))

Max Activating Token Index: 32