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

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

Neuron 2863 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1616383 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0393. Min Act: -0.0000

Data Index: 455566 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0410. Min Act: -0.0000

Data Index: 261745 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0400. Min Act: -0.0000

Data Index: 193907 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0349. Min Act: -0.0000

Data Index: 707248 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0305. Min Act: -0.0000

Data Index: 1140811 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0322. Min Act: -0.0000

Data Index: 87282 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0327. Min Act: -0.0000

Data Index: 624152 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0312. Min Act: -0.0000

Data Index: 21262 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0289. Min Act: -0.0000

Data Index: 794124 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0333. Min Act: -0.0000

Data Index: 1142129 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1027207 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0345. Min Act: -0.0000

Data Index: 973013 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0277. Min Act: -0.0000

Data Index: 850212 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0294. Min Act: -0.0000

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0247. Min Act: -0.0000

Data Index: 1610477 (Python Code)

Max Activating Token Index: 942

Text #16

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0294. Min Act: -0.0000

Data Index: 614904 (C4 (Web Text))

Max Activating Token Index: 981

Text #17

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0257. Min Act: -0.0000

Data Index: 1518234 (Python Code)

Max Activating Token Index: 239

Text #18

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0288. Min Act: -0.0000

Data Index: 1430798 (Python Code)

Max Activating Token Index: 135

Text #19

Max Range: 0.0738. Min Range: -0.0738

Max Act: 0.0276. Min Act: -0.0000

Data Index: 1395008 (Python Code)

Max Activating Token Index: 228