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

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

Neuron 6002 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: 6.1327. Min Range: -6.1327

Max Act: 6.1327. Min Act: -0.0000

Data Index: 777011 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 6.1327. Min Range: -6.1327

Max Act: 6.0460. Min Act: -0.0000

Data Index: 834872 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.5293. Min Act: -0.0000

Data Index: 617104 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.8557. Min Act: -0.0000

Data Index: 808316 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.6818. Min Act: -0.0000

Data Index: 1032712 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.5101. Min Act: -0.0000

Data Index: 1028693 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.5398. Min Act: -0.0000

Data Index: 213440 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.0426. Min Act: -0.0000

Data Index: 569192 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.0027. Min Act: -0.0000

Data Index: 1329673 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.0905. Min Act: -0.0000

Data Index: 616077 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.8896. Min Act: -0.0000

Data Index: 190577 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 6.1327. Min Range: -6.1327

Max Act: 5.4603. Min Act: -0.0000

Data Index: 1197449 (C4 (Web Text))

Max Activating Token Index: 412

Text #12

Max Range: 6.1327. Min Range: -6.1327

Max Act: 3.9492. Min Act: -0.0000

Data Index: 253917 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.6745. Min Act: -0.0000

Data Index: 849633 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.9064. Min Act: -0.0000

Data Index: 209315 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.9263. Min Act: -0.0000

Data Index: 465132 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.5845. Min Act: -0.0000

Data Index: 1116818 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.5457. Min Act: -0.0000

Data Index: 193903 (C4 (Web Text))

Max Activating Token Index: 134

Text #18

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.5820. Min Act: -0.0000

Data Index: 734848 (C4 (Web Text))

Max Activating Token Index: 609

Text #19

Max Range: 6.1327. Min Range: -6.1327

Max Act: 4.4350. Min Act: -0.0000

Data Index: 62354 (C4 (Web Text))

Max Activating Token Index: 609