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

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

Neuron 2378 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: 0.3264. Min Range: -0.3264

Max Act: 0.3264. Min Act: -0.0000

Data Index: 82426 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3234. Min Act: -0.0000

Data Index: 863919 (C4 (Web Text))

Max Activating Token Index: 99

Text #2

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3221. Min Act: -0.0000

Data Index: 129538 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3170. Min Act: -0.0000

Data Index: 513832 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3010. Min Act: -0.0000

Data Index: 32788 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2975. Min Act: -0.0001

Data Index: 131859 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.3018. Min Act: -0.0001

Data Index: 1069759 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2802. Min Act: -0.0000

Data Index: 1314590 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2784. Min Act: -0.0000

Data Index: 590687 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2592. Min Act: -0.0000

Data Index: 820925 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1029932 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2610. Min Act: -0.0000

Data Index: 453623 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2542. Min Act: -0.0000

Data Index: 895035 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1133969 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2356. Min Act: -0.0001

Data Index: 511434 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2434. Min Act: -0.0001

Data Index: 563429 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2475. Min Act: -0.0000

Data Index: 909646 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2361. Min Act: -0.0000

Data Index: 815053 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2344. Min Act: -0.0000

Data Index: 357424 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3264. Min Range: -0.3264

Max Act: 0.2275. Min Act: -0.0000

Data Index: 649720 (C4 (Web Text))

Max Activating Token Index: 144