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

Dataset: The Pile

Neuron 3155 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: 1.0472. Min Range: -1.0472

Max Act: 1.0472. Min Act: -0.0000

Data Index: 314645 (The Pile)

Max Activating Token Index: 690

Text #1

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1442339 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.9268. Min Act: -0.0000

Data Index: 466890 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8474. Min Act: -0.0000

Data Index: 560877 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8716. Min Act: -0.0000

Data Index: 1175942 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8410. Min Act: 0.0001

Data Index: 1041832 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.8645. Min Act: -0.0000

Data Index: 1679774 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7704. Min Act: -0.0000

Data Index: 760632 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7806. Min Act: -0.0000

Data Index: 84250 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7748. Min Act: -0.0000

Data Index: 19118 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7850. Min Act: -0.0000

Data Index: 956552 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7419. Min Act: -0.0000

Data Index: 1881279 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7240. Min Act: -0.0000

Data Index: 433259 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6951. Min Act: -0.0000

Data Index: 1046533 (The Pile)

Max Activating Token Index: 465

Text #14

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1273613 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1539565 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6976. Min Act: -0.0000

Data Index: 720053 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6682. Min Act: -0.0000

Data Index: 81282 (The Pile)

Max Activating Token Index: 382

Text #18

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6906. Min Act: -0.0000

Data Index: 1736600 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 1.0472. Min Range: -1.0472

Max Act: 0.6341. Min Act: -0.0000

Data Index: 200612 (The Pile)

Max Activating Token Index: 987