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

Dataset: The Pile

Neuron 171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6404. Min Act: -0.0000

Data Index: 1463418 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.8471. Min Act: -0.0000

Data Index: 90656 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.4464. Min Act: -0.0000

Data Index: 1928260 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.1042. Min Act: -0.0000

Data Index: 464280 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.0540. Min Act: -0.0000

Data Index: 733033 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.8806. Min Act: -0.0000

Data Index: 593655 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.6562. Min Act: -0.0000

Data Index: 209227 (The Pile)

Max Activating Token Index: 977

Text #7

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.7106. Min Act: -0.0000

Data Index: 664423 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.8896. Min Act: -0.0000

Data Index: 1522665 (The Pile)

Max Activating Token Index: 117

Text #9

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.6176. Min Act: -0.0000

Data Index: 1340906 (The Pile)

Max Activating Token Index: 113

Text #10

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.4589. Min Act: -0.0000

Data Index: 497474 (The Pile)

Max Activating Token Index: 820

Text #11

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.4027. Min Act: -0.0000

Data Index: 400131 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.2831. Min Act: -0.0000

Data Index: 1231 (The Pile)

Max Activating Token Index: 89

Text #13

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.0939. Min Act: -0.0000

Data Index: 1269984 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 5.8471. Min Range: -5.8471

Max Act: 4.1724. Min Act: -0.0000

Data Index: 1356982 (The Pile)

Max Activating Token Index: 82

Text #15

Max Range: 5.8471. Min Range: -5.8471

Max Act: 3.9040. Min Act: -0.0000

Data Index: 1465900 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 5.8471. Min Range: -5.8471

Max Act: 3.6753. Min Act: -0.0000

Data Index: 1866589 (The Pile)

Max Activating Token Index: 629

Text #17

Max Range: 5.8471. Min Range: -5.8471

Max Act: 3.7881. Min Act: -0.0000

Data Index: 1675883 (The Pile)

Max Activating Token Index: 551

Text #18

Max Range: 5.8471. Min Range: -5.8471

Max Act: 3.5395. Min Act: -0.0000

Data Index: 1022901 (The Pile)

Max Activating Token Index: 530

Text #19

Max Range: 5.8471. Min Range: -5.8471

Max Act: 3.6738. Min Act: -0.0000

Data Index: 1944852 (The Pile)

Max Activating Token Index: 360