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

Dataset: The Pile

Neuron 334 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8255. Min Act: -0.0000

Data Index: 957268 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8235. Min Act: -0.0000

Data Index: 114106 (The Pile)

Max Activating Token Index: 453

Text #2

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8337. Min Act: -0.0000

Data Index: 1326107 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1789226 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1050702 (The Pile)

Max Activating Token Index: 517

Text #5

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7102. Min Act: -0.0000

Data Index: 343978 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1681648 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.8206. Min Act: 0.0000

Data Index: 65641 (The Pile)

Max Activating Token Index: 811

Text #8

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1658938 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1358658 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7107. Min Act: -0.0000

Data Index: 326942 (The Pile)

Max Activating Token Index: 401

Text #11

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7261. Min Act: -0.0000

Data Index: 91899 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6476. Min Act: -0.0000

Data Index: 374603 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.7105. Min Act: -0.0000

Data Index: 233864 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6576. Min Act: -0.0000

Data Index: 1813198 (The Pile)

Max Activating Token Index: 170

Text #15

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1581968 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5714. Min Act: -0.0000

Data Index: 770453 (The Pile)

Max Activating Token Index: 495

Text #17

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6497. Min Act: -0.0000

Data Index: 808957 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.6335. Min Act: -0.0000

Data Index: 700666 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.8337. Min Range: -0.8337

Max Act: 0.5905. Min Act: -0.0000

Data Index: 1045752 (The Pile)

Max Activating Token Index: 361