Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 910 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.6861. Min Act: -0.0000

Data Index: 1420888 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5872. Min Act: -0.0000

Data Index: 334409 (The Pile)

Max Activating Token Index: 475

Text #2

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5792. Min Act: -0.0000

Data Index: 15992 (The Pile)

Max Activating Token Index: 895

Text #3

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.5076. Min Act: -0.0000

Data Index: 1579377 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3909. Min Act: -0.0000

Data Index: 99857 (The Pile)

Max Activating Token Index: 928

Text #5

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1110518 (The Pile)

Max Activating Token Index: 400

Text #6

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3815. Min Act: -0.0000

Data Index: 957360 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3632. Min Act: -0.0000

Data Index: 606814 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1073539 (The Pile)

Max Activating Token Index: 761

Text #9

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2909. Min Act: -0.0000

Data Index: 524106 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2218. Min Act: -0.0000

Data Index: 1365516 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2408. Min Act: -0.0000

Data Index: 1855341 (The Pile)

Max Activating Token Index: 734

Text #12

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2979. Min Act: -0.0000

Data Index: 732748 (The Pile)

Max Activating Token Index: 601

Text #13

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1682340 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.1684. Min Act: -0.0000

Data Index: 749659 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2758. Min Act: 0.0000

Data Index: 1180023 (The Pile)

Max Activating Token Index: 701

Text #16

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2651. Min Act: -0.0000

Data Index: 604001 (The Pile)

Max Activating Token Index: 997

Text #17

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.2648. Min Act: -0.0000

Data Index: 87306 (The Pile)

Max Activating Token Index: 738

Text #18

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.1709. Min Act: -0.0000

Data Index: 683196 (The Pile)

Max Activating Token Index: 127

Text #19

Max Range: 1.6861. Min Range: -1.6861

Max Act: 1.1570. Min Act: -0.0000

Data Index: 1344337 (The Pile)

Max Activating Token Index: 272