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

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

Neuron 1229 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.4442. Min Act: -0.0000

Data Index: 196605 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3097. Min Act: -0.0000

Data Index: 632415 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3978. Min Act: -0.0000

Data Index: 113749 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3429. Min Act: -0.0000

Data Index: 65241 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2363. Min Act: -0.0000

Data Index: 735951 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2776. Min Act: -0.0000

Data Index: 1288544 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1049703 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2454. Min Act: -0.0000

Data Index: 88 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.3121. Min Act: -0.0000

Data Index: 316146 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2618. Min Act: -0.0000

Data Index: 55986 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2915. Min Act: -0.0000

Data Index: 465080 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1291001 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2364. Min Act: -0.0000

Data Index: 845853 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1289784 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1295134 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2187. Min Act: -0.0000

Data Index: 1112461 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1489. Min Act: -0.0000

Data Index: 849636 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.2477. Min Act: -0.0000

Data Index: 494862 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1396. Min Act: -0.0000

Data Index: 1094811 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.1397. Min Act: -0.0000

Data Index: 163331 (C4 (Web Text))

Max Activating Token Index: 650