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

Dataset: The Pile

Neuron 2243 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: 1.2284. Min Range: -1.2284

Max Act: 1.2284. Min Act: 0.0000

Data Index: 148665 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0444. Min Act: -0.0000

Data Index: 219079 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 1.2284. Min Range: -1.2284

Max Act: 1.0156. Min Act: -0.0000

Data Index: 1762165 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1410083 (The Pile)

Max Activating Token Index: 193

Text #4

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1000487 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.9003. Min Act: -0.0000

Data Index: 557626 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8912. Min Act: -0.0000

Data Index: 63955 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.8082. Min Act: 0.0000

Data Index: 474799 (The Pile)

Max Activating Token Index: 651

Text #8

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.7842. Min Act: -0.0000

Data Index: 1786912 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1482178 (The Pile)

Max Activating Token Index: 861

Text #10

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.7775. Min Act: -0.0000

Data Index: 972568 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6997. Min Act: -0.0000

Data Index: 1450404 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6956. Min Act: 0.0000

Data Index: 415481 (The Pile)

Max Activating Token Index: 928

Text #13

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.7008. Min Act: -0.0000

Data Index: 603524 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6760. Min Act: 0.0000

Data Index: 1692309 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1093948 (The Pile)

Max Activating Token Index: 366

Text #16

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6923. Min Act: 0.0001

Data Index: 382249 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.7078. Min Act: -0.0000

Data Index: 1033393 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1545331 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 1.2284. Min Range: -1.2284

Max Act: 0.6471. Min Act: -0.0000

Data Index: 1606473 (The Pile)

Max Activating Token Index: 826