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

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

Neuron 246 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: 0.2965. Min Range: -0.2965

Max Act: 0.2965. Min Act: -0.0001

Data Index: 546225 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2863. Min Act: -0.0001

Data Index: 990257 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2710. Min Act: -0.0001

Data Index: 961174 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2738. Min Act: -0.0001

Data Index: 450214 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2665. Min Act: -0.0001

Data Index: 568890 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2574. Min Act: -0.0001

Data Index: 717331 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2544. Min Act: -0.0001

Data Index: 705622 (C4 (Web Text))

Max Activating Token Index: 939

Text #7

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1040611 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2369. Min Act: -0.0001

Data Index: 42842 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2460. Min Act: -0.0001

Data Index: 1093732 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2367. Min Act: -0.0001

Data Index: 811407 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2532. Min Act: -0.0001

Data Index: 887248 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2352. Min Act: -0.0001

Data Index: 291093 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2415. Min Act: -0.0001

Data Index: 982387 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2397. Min Act: -0.0001

Data Index: 538929 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2364. Min Act: -0.0001

Data Index: 103377 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2182. Min Act: -0.0001

Data Index: 490322 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2299. Min Act: -0.0001

Data Index: 1160154 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2228. Min Act: -0.0001

Data Index: 776887 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2132. Min Act: -0.0001

Data Index: 264422 (C4 (Web Text))

Max Activating Token Index: 536