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

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

Neuron 1327 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0709. Min Range: -1.0709

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1336874 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9824. Min Act: -0.0000

Data Index: 767556 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1033152 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8454. Min Act: -0.0000

Data Index: 704550 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1220354 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7140. Min Act: -0.0000

Data Index: 939724 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7836. Min Act: -0.0000

Data Index: 890551 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.8100. Min Act: -0.0000

Data Index: 740089 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.7053. Min Act: -0.0000

Data Index: 911970 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6746. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1134278 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6018. Min Act: -0.0000

Data Index: 1317110 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1096103 (C4 (Web Text))

Max Activating Token Index: 1010

Text #13

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.5443. Min Act: -0.0000

Data Index: 248428 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6275. Min Act: -0.0000

Data Index: 409944 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6120. Min Act: -0.0000

Data Index: 965065 (C4 (Web Text))

Max Activating Token Index: 938

Text #16

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6046. Min Act: -0.0000

Data Index: 779800 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6215. Min Act: -0.0000

Data Index: 662753 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.6454. Min Act: -0.0000

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 1.0709. Min Range: -1.0709

Max Act: 0.5969. Min Act: -0.0000

Data Index: 212153 (C4 (Web Text))

Max Activating Token Index: 644