Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2111 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.7656. Min Act: -0.0000

Data Index: 615365 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.0410. Min Act: -0.0000

Data Index: 438838 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.3117. Min Act: -0.0000

Data Index: 791022 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 4.7656. Min Range: -4.7656

Max Act: 4.7061. Min Act: -0.0000

Data Index: 13130 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.9323. Min Act: -0.0000

Data Index: 1381393 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.9354. Min Act: -0.0000

Data Index: 1371683 (Python Code)

Max Activating Token Index: 786

Text #6

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.8129. Min Act: -0.0000

Data Index: 1331833 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.7069. Min Act: -0.0000

Data Index: 46093 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.4403. Min Act: -0.0000

Data Index: 251588 (C4 (Web Text))

Max Activating Token Index: 535

Text #9

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.4548. Min Act: -0.0000

Data Index: 446417 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.3174. Min Act: -0.0000

Data Index: 1638703 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.1356. Min Act: -0.0000

Data Index: 716143 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 4.7656. Min Range: -4.7656

Max Act: 2.9401. Min Act: -0.0000

Data Index: 1323419 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 4.7656. Min Range: -4.7656

Max Act: 2.9217. Min Act: -0.0000

Data Index: 503604 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.0945. Min Act: -0.0000

Data Index: 986169 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.0663. Min Act: -0.0000

Data Index: 1084354 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 4.7656. Min Range: -4.7656

Max Act: 2.8218. Min Act: -0.0000

Data Index: 1621709 (Python Code)

Max Activating Token Index: 252

Text #17

Max Range: 4.7656. Min Range: -4.7656

Max Act: 2.9496. Min Act: -0.0000

Data Index: 360192 (C4 (Web Text))

Max Activating Token Index: 441

Text #18

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.1736. Min Act: -0.0000

Data Index: 1460024 (Python Code)

Max Activating Token Index: 362

Text #19

Max Range: 4.7656. Min Range: -4.7656

Max Act: 3.0462. Min Act: -0.0000

Data Index: 629185 (C4 (Web Text))

Max Activating Token Index: 517