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

Dataset: The Pile

Neuron 2903 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.7312. Min Act: -0.0000

Data Index: 1355114 (The Pile)

Max Activating Token Index: 43

Text #1

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.6801. Min Act: -0.0000

Data Index: 212037 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.4972. Min Act: 0.0000

Data Index: 1122621 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5465. Min Act: -0.0000

Data Index: 638951 (The Pile)

Max Activating Token Index: 574

Text #4

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5065. Min Act: -0.0000

Data Index: 1930276 (The Pile)

Max Activating Token Index: 14

Text #5

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.4096. Min Act: -0.0000

Data Index: 956402 (The Pile)

Max Activating Token Index: 101

Text #6

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.8960. Min Act: 0.0000

Data Index: 1245473 (The Pile)

Max Activating Token Index: 16

Text #7

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5396. Min Act: 0.0001

Data Index: 286793 (The Pile)

Max Activating Token Index: 16

Text #8

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5573. Min Act: 0.0000

Data Index: 1816888 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5324. Min Act: -0.0000

Data Index: 1285485 (The Pile)

Max Activating Token Index: 779

Text #10

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.5020. Min Act: -0.0000

Data Index: 32888 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.4442. Min Act: -0.0000

Data Index: 1070536 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.0915. Min Act: 0.0000

Data Index: 1742361 (The Pile)

Max Activating Token Index: 70

Text #13

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.3826. Min Act: -0.0000

Data Index: 247423 (The Pile)

Max Activating Token Index: 153

Text #14

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.2874. Min Act: -0.0000

Data Index: 313381 (The Pile)

Max Activating Token Index: 637

Text #15

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.1625. Min Act: -0.0000

Data Index: 325795 (The Pile)

Max Activating Token Index: 767

Text #16

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.2789. Min Act: -0.0000

Data Index: 972465 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.2501. Min Act: -0.0000

Data Index: 1354915 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.3881. Min Act: -0.0000

Data Index: 1605345 (The Pile)

Max Activating Token Index: 820

Text #19

Max Range: 3.8960. Min Range: -3.8960

Max Act: 3.1023. Min Act: 0.0001

Data Index: 96238 (The Pile)

Max Activating Token Index: 58