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

Dataset: The Pile

Neuron 1050 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.6662. Min Act: -0.0000

Data Index: 431659 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1132291 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.3988. Min Act: -0.0000

Data Index: 1035255 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.4010. Min Act: -0.0000

Data Index: 1195675 (The Pile)

Max Activating Token Index: 602

Text #4

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.3572. Min Act: -0.0000

Data Index: 926579 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1962. Min Act: -0.0000

Data Index: 1386349 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.2682. Min Act: -0.0000

Data Index: 931964 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.2792. Min Act: -0.0000

Data Index: 1988163 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1206. Min Act: -0.0000

Data Index: 993315 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1007696 (The Pile)

Max Activating Token Index: 505

Text #10

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1605. Min Act: -0.0000

Data Index: 541886 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1539. Min Act: -0.0000

Data Index: 216120 (The Pile)

Max Activating Token Index: 962

Text #12

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.2165. Min Act: -0.0000

Data Index: 31387 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1395. Min Act: -0.0000

Data Index: 892516 (The Pile)

Max Activating Token Index: 884

Text #14

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1255. Min Act: -0.0000

Data Index: 664453 (The Pile)

Max Activating Token Index: 587

Text #15

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1962. Min Act: -0.0000

Data Index: 510262 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1214. Min Act: -0.0000

Data Index: 1607753 (The Pile)

Max Activating Token Index: 132

Text #17

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1305. Min Act: -0.0000

Data Index: 526946 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.1147. Min Act: -0.0000

Data Index: 506640 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 1.6662. Min Range: -1.6662

Max Act: 1.0245. Min Act: -0.0000

Data Index: 1149781 (The Pile)

Max Activating Token Index: 718