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

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

Neuron 3395 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.3204. Min Act: -0.0000

Data Index: 127912 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.4278. Min Act: -0.0000

Data Index: 1144465 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.2446. Min Act: -0.0000

Data Index: 759135 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.2234. Min Act: -0.0000

Data Index: 1211213 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.1814. Min Act: -0.0000

Data Index: 617354 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.0018. Min Act: -0.0000

Data Index: 1030373 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.4278. Min Range: -1.4278

Max Act: 1.0250. Min Act: -0.0000

Data Index: 777032 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1235759 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.9222. Min Act: -0.0000

Data Index: 373342 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1342 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1120996 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8517. Min Act: -0.0000

Data Index: 121927 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8791. Min Act: -0.0000

Data Index: 1339160 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8498. Min Act: -0.0000

Data Index: 1342469 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8704. Min Act: -0.0000

Data Index: 438435 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1281297 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.7469. Min Act: -0.0000

Data Index: 62233 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.7333. Min Act: -0.0000

Data Index: 962763 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.7328. Min Act: -0.0000

Data Index: 1141681 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 1.4278. Min Range: -1.4278

Max Act: 0.7149. Min Act: -0.0000

Data Index: 962259 (C4 (Web Text))

Max Activating Token Index: 296