Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 671 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1351585 (C4 (Web Text))

Max Activating Token Index: 857

Text #1

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3286. Min Act: -0.0000

Data Index: 12883 (C4 (Web Text))

Max Activating Token Index: 173

Text #2

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1033451 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3038. Min Act: 0.0000

Data Index: 1157965 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3049. Min Act: 0.0000

Data Index: 1201608 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2932. Min Act: -0.0000

Data Index: 456379 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2762. Min Act: 0.0000

Data Index: 768479 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2520. Min Act: 0.0000

Data Index: 688020 (C4 (Web Text))

Max Activating Token Index: 82

Text #8

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2681. Min Act: -0.0000

Data Index: 709963 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2476. Min Act: -0.0000

Data Index: 464156 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1236568 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2399. Min Act: 0.0000

Data Index: 373434 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2376. Min Act: -0.0000

Data Index: 1336148 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2350. Min Act: -0.0000

Data Index: 932510 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2311. Min Act: -0.0000

Data Index: 726209 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2153. Min Act: -0.0000

Data Index: 1315899 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2192. Min Act: -0.0000

Data Index: 848832 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1341549 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2331. Min Act: -0.0000

Data Index: 284776 (C4 (Web Text))

Max Activating Token Index: 306

Text #19

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1061965 (C4 (Web Text))

Max Activating Token Index: 168