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

Dataset: The Pile

Neuron 4138 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: 7.0140. Min Range: -7.0140

Max Act: 7.0140. Min Act: -0.0000

Data Index: 1855722 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 7.0140. Min Range: -7.0140

Max Act: 5.3193. Min Act: -0.0000

Data Index: 1437711 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 7.0140. Min Range: -7.0140

Max Act: 5.5148. Min Act: -0.0000

Data Index: 966668 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 7.0140. Min Range: -7.0140

Max Act: 5.7445. Min Act: -0.0000

Data Index: 1523352 (The Pile)

Max Activating Token Index: 964

Text #4

Max Range: 7.0140. Min Range: -7.0140

Max Act: 5.2060. Min Act: -0.0000

Data Index: 804940 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.9430. Min Act: -0.0000

Data Index: 373507 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.9273. Min Act: -0.0000

Data Index: 1118399 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.3983. Min Act: -0.0000

Data Index: 189508 (The Pile)

Max Activating Token Index: 918

Text #8

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.4967. Min Act: -0.0000

Data Index: 357522 (The Pile)

Max Activating Token Index: 297

Text #9

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.5467. Min Act: -0.0000

Data Index: 1337937 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.6118. Min Act: -0.0000

Data Index: 1607304 (The Pile)

Max Activating Token Index: 171

Text #11

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.1431. Min Act: -0.0000

Data Index: 259534 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.1391. Min Act: -0.0000

Data Index: 762819 (The Pile)

Max Activating Token Index: 993

Text #13

Max Range: 7.0140. Min Range: -7.0140

Max Act: 3.8465. Min Act: -0.0000

Data Index: 1546935 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.2492. Min Act: -0.0000

Data Index: 1646751 (The Pile)

Max Activating Token Index: 156

Text #15

Max Range: 7.0140. Min Range: -7.0140

Max Act: 4.3505. Min Act: -0.0000

Data Index: 1140691 (The Pile)

Max Activating Token Index: 1007

Text #16

Max Range: 7.0140. Min Range: -7.0140

Max Act: 3.3425. Min Act: -0.0000

Data Index: 123042 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 7.0140. Min Range: -7.0140

Max Act: 3.9404. Min Act: -0.0000

Data Index: 864409 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 7.0140. Min Range: -7.0140

Max Act: 3.9147. Min Act: -0.0000

Data Index: 1411026 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 7.0140. Min Range: -7.0140

Max Act: 3.7276. Min Act: -0.0000

Data Index: 254658 (The Pile)

Max Activating Token Index: 564