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

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

Neuron 2659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.3198. Min Act: -0.0001

Data Index: 552983 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2704. Min Act: -0.0000

Data Index: 499375 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2553. Min Act: -0.0000

Data Index: 902083 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2497. Min Act: -0.0000

Data Index: 807165 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2744. Min Act: -0.0001

Data Index: 1022626 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2557. Min Act: -0.0000

Data Index: 130284 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2498. Min Act: -0.0001

Data Index: 3677 (C4 (Web Text))

Max Activating Token Index: 522

Text #7

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2509. Min Act: -0.0000

Data Index: 651777 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2443. Min Act: -0.0000

Data Index: 1261813 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2459. Min Act: -0.0001

Data Index: 716073 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2373. Min Act: -0.0001

Data Index: 119153 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2519. Min Act: -0.0001

Data Index: 253472 (C4 (Web Text))

Max Activating Token Index: 773

Text #12

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2424. Min Act: -0.0001

Data Index: 95487 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2390. Min Act: -0.0000

Data Index: 776980 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1294344 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2360. Min Act: -0.0001

Data Index: 206886 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2330. Min Act: -0.0000

Data Index: 554720 (C4 (Web Text))

Max Activating Token Index: 442

Text #17

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2234. Min Act: -0.0001

Data Index: 364516 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2461. Min Act: -0.0001

Data Index: 534946 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.3198. Min Range: -0.3198

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1151844 (C4 (Web Text))

Max Activating Token Index: 586