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

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

Neuron 1127 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.3776. Min Act: -0.0000

Data Index: 937086 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.2603. Min Act: -0.0000

Data Index: 218596 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.3247. Min Act: -0.0000

Data Index: 1231295 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.1890. Min Act: -0.0000

Data Index: 1142689 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0543. Min Act: -0.0000

Data Index: 740072 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0335. Min Act: -0.0000

Data Index: 384122 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0329. Min Act: -0.0000

Data Index: 612438 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0346. Min Act: -0.0000

Data Index: 869356 (C4 (Web Text))

Max Activating Token Index: 446

Text #8

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0330. Min Act: -0.0000

Data Index: 1098347 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0593. Min Act: -0.0000

Data Index: 358573 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9802. Min Act: -0.0000

Data Index: 44574 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9269. Min Act: -0.0000

Data Index: 322911 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1266178 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9523. Min Act: -0.0000

Data Index: 288707 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9382. Min Act: -0.0000

Data Index: 34411 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9353. Min Act: -0.0000

Data Index: 944222 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1060269 (C4 (Web Text))

Max Activating Token Index: 224

Text #17

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8605. Min Act: -0.0000

Data Index: 131744 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1240624 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9211. Min Act: -0.0000

Data Index: 635975 (C4 (Web Text))

Max Activating Token Index: 272