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

Dataset: The Pile

Neuron 3287 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: 0.4442. Min Range: -0.4442

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1452755 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.4442. Min Act: -0.0000

Data Index: 945313 (The Pile)

Max Activating Token Index: 669

Text #2

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3759. Min Act: -0.0000

Data Index: 14646 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3666. Min Act: -0.0000

Data Index: 545561 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1637618 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3157. Min Act: -0.0000

Data Index: 304455 (The Pile)

Max Activating Token Index: 477

Text #6

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3252. Min Act: -0.0000

Data Index: 860736 (The Pile)

Max Activating Token Index: 593

Text #7

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1485638 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3142. Min Act: -0.0000

Data Index: 138070 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1110748 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2963. Min Act: -0.0000

Data Index: 22036 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1765110 (The Pile)

Max Activating Token Index: 120

Text #12

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2927. Min Act: -0.0000

Data Index: 204568 (The Pile)

Max Activating Token Index: 492

Text #13

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1824834 (The Pile)

Max Activating Token Index: 114

Text #14

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3091. Min Act: -0.0000

Data Index: 265793 (The Pile)

Max Activating Token Index: 83

Text #15

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3104. Min Act: -0.0000

Data Index: 399050 (The Pile)

Max Activating Token Index: 40

Text #16

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1470297 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2801. Min Act: -0.0000

Data Index: 519278 (The Pile)

Max Activating Token Index: 112

Text #18

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.3395. Min Act: -0.0000

Data Index: 1308359 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.4442. Min Range: -0.4442

Max Act: 0.2875. Min Act: -0.0000

Data Index: 58627 (The Pile)

Max Activating Token Index: 177