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

Dataset: The Pile

Neuron 260 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.8890. Min Act: -0.0000

Data Index: 1182111 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7369. Min Act: -0.0000

Data Index: 1355135 (The Pile)

Max Activating Token Index: 936

Text #2

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7893. Min Act: -0.0000

Data Index: 411830 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6827. Min Act: -0.0000

Data Index: 250949 (The Pile)

Max Activating Token Index: 164

Text #4

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1061279 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1534433 (The Pile)

Max Activating Token Index: 510

Text #6

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6948. Min Act: -0.0000

Data Index: 222333 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1405732 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.5761. Min Act: -0.0000

Data Index: 311245 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1421690 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1287040 (The Pile)

Max Activating Token Index: 649

Text #11

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1746082 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1571182 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.5980. Min Act: -0.0000

Data Index: 919565 (The Pile)

Max Activating Token Index: 383

Text #14

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6677. Min Act: -0.0000

Data Index: 979224 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6066. Min Act: -0.0000

Data Index: 742396 (The Pile)

Max Activating Token Index: 268

Text #16

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6417. Min Act: -0.0000

Data Index: 880820 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1418930 (The Pile)

Max Activating Token Index: 448

Text #18

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6536. Min Act: -0.0000

Data Index: 850008 (The Pile)

Max Activating Token Index: 880

Text #19

Max Range: 0.8890. Min Range: -0.8890

Max Act: 0.6109. Min Act: -0.0000

Data Index: 355046 (The Pile)

Max Activating Token Index: 93