Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1370 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.3202. Min Act: -0.0000

Data Index: 103044 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.3085. Min Act: -0.0000

Data Index: 481915 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2800. Min Act: -0.0000

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2736. Min Act: -0.0000

Data Index: 883916 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2619. Min Act: -0.0000

Data Index: 1208476 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2507. Min Act: -0.0000

Data Index: 1215703 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2673. Min Act: -0.0001

Data Index: 740145 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2563. Min Act: -0.0000

Data Index: 343957 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2638. Min Act: -0.0000

Data Index: 133761 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2627. Min Act: -0.0001

Data Index: 209624 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1282960 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2403. Min Act: -0.0000

Data Index: 897635 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2569. Min Act: -0.0000

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2470. Min Act: -0.0000

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2463. Min Act: -0.0001

Data Index: 794379 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2435. Min Act: -0.0000

Data Index: 517932 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2365. Min Act: -0.0001

Data Index: 698801 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2303. Min Act: -0.0001

Data Index: 196873 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2353. Min Act: -0.0001

Data Index: 1263942 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.3202. Min Range: -0.3202

Max Act: 0.2487. Min Act: -0.0000

Data Index: 680539 (C4 (Web Text))

Max Activating Token Index: 623