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

Dataset: The Pile

Neuron 1155 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.1762. Min Act: -0.0000

Data Index: 362050 (The Pile)

Max Activating Token Index: 86

Text #1

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1018642 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.0442. Min Act: -0.0000

Data Index: 263113 (The Pile)

Max Activating Token Index: 338

Text #3

Max Range: 1.1762. Min Range: -1.1762

Max Act: 1.0463. Min Act: -0.0000

Data Index: 134008 (The Pile)

Max Activating Token Index: 773

Text #4

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9683. Min Act: -0.0000

Data Index: 1727392 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1049517 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1510288 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8479. Min Act: -0.0000

Data Index: 1192319 (The Pile)

Max Activating Token Index: 40

Text #8

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8336. Min Act: -0.0000

Data Index: 1026317 (The Pile)

Max Activating Token Index: 154

Text #9

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8007. Min Act: -0.0000

Data Index: 167612 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1158482 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7934. Min Act: -0.0000

Data Index: 70518 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8137. Min Act: -0.0001

Data Index: 1682221 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8039. Min Act: -0.0000

Data Index: 987075 (The Pile)

Max Activating Token Index: 658

Text #14

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7686. Min Act: -0.0000

Data Index: 226678 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7352. Min Act: -0.0000

Data Index: 752804 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1399517 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1362911 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1115503 (The Pile)

Max Activating Token Index: 684

Text #19

Max Range: 1.1762. Min Range: -1.1762

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1833398 (The Pile)

Max Activating Token Index: 818