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

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

Neuron 1790 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: 0.2866. Min Range: -0.2866

Max Act: 0.2866. Min Act: -0.0001

Data Index: 757677 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2705. Min Act: -0.0001

Data Index: 864467 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2551. Min Act: -0.0001

Data Index: 1062856 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2753. Min Act: -0.0001

Data Index: 246033 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2447. Min Act: -0.0001

Data Index: 206100 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2386. Min Act: -0.0001

Data Index: 819026 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2402. Min Act: -0.0001

Data Index: 188336 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2373. Min Act: 0.0000

Data Index: 885631 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1331669 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1234158 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2301. Min Act: -0.0001

Data Index: 793266 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1266301 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2232. Min Act: 0.0000

Data Index: 1132658 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2245. Min Act: -0.0001

Data Index: 75303 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2216. Min Act: -0.0001

Data Index: 674141 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2114. Min Act: -0.0001

Data Index: 910778 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2258. Min Act: -0.0001

Data Index: 995059 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1346118 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2323. Min Act: -0.0001

Data Index: 301882 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.2866. Min Range: -0.2866

Max Act: 0.2144. Min Act: -0.0001

Data Index: 1038690 (C4 (Web Text))

Max Activating Token Index: 782