Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3993 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.4915. Min Act: -0.0000

Data Index: 1302944 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1828381 (The Pile)

Max Activating Token Index: 628

Text #2

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3276. Min Act: -0.0000

Data Index: 696443 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1688157 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1996367 (The Pile)

Max Activating Token Index: 759

Text #5

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3327. Min Act: -0.0000

Data Index: 648935 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.3592. Min Act: -0.0000

Data Index: 340798 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1763346 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2120. Min Act: -0.0000

Data Index: 1455485 (The Pile)

Max Activating Token Index: 551

Text #9

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1550405 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2604. Min Act: -0.0000

Data Index: 370802 (The Pile)

Max Activating Token Index: 817

Text #11

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1300. Min Act: -0.0000

Data Index: 1827825 (The Pile)

Max Activating Token Index: 522

Text #12

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1703. Min Act: -0.0000

Data Index: 1652290 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1519. Min Act: -0.0000

Data Index: 719189 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1134845 (The Pile)

Max Activating Token Index: 510

Text #15

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.2241. Min Act: -0.0000

Data Index: 762725 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1327. Min Act: -0.0000

Data Index: 634533 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1415. Min Act: -0.0000

Data Index: 841683 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.0649. Min Act: -0.0000

Data Index: 144568 (The Pile)

Max Activating Token Index: 636

Text #19

Max Range: 1.6361. Min Range: -1.6361

Max Act: 1.1879. Min Act: -0.0000

Data Index: 520504 (The Pile)

Max Activating Token Index: 538