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

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

Neuron 2519 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.9782. Min Act: -0.0000

Data Index: 1485076 (Python Code)

Max Activating Token Index: 268

Text #1

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8442. Min Act: -0.0000

Data Index: 1477023 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1424761 (Python Code)

Max Activating Token Index: 247

Text #3

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1625809 (Python Code)

Max Activating Token Index: 258

Text #4

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8304. Min Act: -0.0000

Data Index: 1648232 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8428. Min Act: -0.0000

Data Index: 1489696 (Python Code)

Max Activating Token Index: 584

Text #6

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1425474 (Python Code)

Max Activating Token Index: 255

Text #7

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1627482 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1582459 (Python Code)

Max Activating Token Index: 615

Text #9

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1492359 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1482388 (Python Code)

Max Activating Token Index: 402

Text #11

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1465050 (Python Code)

Max Activating Token Index: 201

Text #12

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1590093 (Python Code)

Max Activating Token Index: 221

Text #13

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1568963 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1540940 (Python Code)

Max Activating Token Index: 595

Text #15

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1630970 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7978. Min Act: -0.0000

Data Index: 1392095 (Python Code)

Max Activating Token Index: 313

Text #17

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1520240 (Python Code)

Max Activating Token Index: 285

Text #18

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7376. Min Act: -0.0000

Data Index: 1592228 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 0.9782. Min Range: -0.9782

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1531821 (Python Code)

Max Activating Token Index: 355