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

Dataset: The Pile

Neuron 155 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: 0.5148. Min Range: -0.5148

Max Act: 0.4782. Min Act: -0.0000

Data Index: 415676 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.5148. Min Act: -0.0000

Data Index: 740568 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1478029 (The Pile)

Max Activating Token Index: 123

Text #3

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4590. Min Act: -0.0000

Data Index: 690617 (The Pile)

Max Activating Token Index: 750

Text #4

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1739511 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1268294 (The Pile)

Max Activating Token Index: 48

Text #6

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1903117 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4854. Min Act: -0.0000

Data Index: 1510765 (The Pile)

Max Activating Token Index: 268

Text #8

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4849. Min Act: -0.0000

Data Index: 1638689 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4678. Min Act: -0.0000

Data Index: 454914 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4231. Min Act: -0.0000

Data Index: 608954 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4342. Min Act: -0.0000

Data Index: 795938 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1310237 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4024. Min Act: -0.0000

Data Index: 955502 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1490755 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1733352 (The Pile)

Max Activating Token Index: 788

Text #16

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1111756 (The Pile)

Max Activating Token Index: 367

Text #17

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3839. Min Act: -0.0000

Data Index: 287358 (The Pile)

Max Activating Token Index: 966

Text #18

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.3853. Min Act: -0.0000

Data Index: 281591 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.5148. Min Range: -0.5148

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1474216 (The Pile)

Max Activating Token Index: 753