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

Dataset: The Pile

Neuron 670 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0455. Min Act: -0.0000

Data Index: 173554 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 1.0474. Min Range: -1.0474

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1442931 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9421. Min Act: -0.0000

Data Index: 109459 (The Pile)

Max Activating Token Index: 608

Text #3

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.9407. Min Act: -0.0000

Data Index: 205068 (The Pile)

Max Activating Token Index: 646

Text #4

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8652. Min Act: -0.0000

Data Index: 1776002 (The Pile)

Max Activating Token Index: 960

Text #5

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7754. Min Act: -0.0000

Data Index: 238838 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7433. Min Act: -0.0000

Data Index: 934277 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1334492 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1097004 (The Pile)

Max Activating Token Index: 410

Text #9

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8874. Min Act: -0.0000

Data Index: 1758617 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1655680 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8513. Min Act: -0.0000

Data Index: 924053 (The Pile)

Max Activating Token Index: 973

Text #12

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1493115 (The Pile)

Max Activating Token Index: 247

Text #13

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1735454 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7965. Min Act: -0.0000

Data Index: 538014 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7594. Min Act: -0.0000

Data Index: 753953 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.7601. Min Act: -0.0000

Data Index: 45877 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.8255. Min Act: -0.0000

Data Index: 296711 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6478. Min Act: -0.0000

Data Index: 260843 (The Pile)

Max Activating Token Index: 352

Text #19

Max Range: 1.0474. Min Range: -1.0474

Max Act: 0.6040. Min Act: -0.0000

Data Index: 904163 (The Pile)

Max Activating Token Index: 983