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

Dataset: The Pile

Neuron 48 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: 1.6293. Min Range: -1.6293

Max Act: 1.6293. Min Act: -0.0000

Data Index: 324287 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.3162. Min Act: -0.0000

Data Index: 891584 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.3385. Min Act: -0.0000

Data Index: 364044 (The Pile)

Max Activating Token Index: 399

Text #3

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.4166. Min Act: -0.0000

Data Index: 263020 (The Pile)

Max Activating Token Index: 155

Text #4

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.0824. Min Act: -0.0000

Data Index: 651651 (The Pile)

Max Activating Token Index: 963

Text #5

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1494. Min Act: -0.0000

Data Index: 1623356 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1642283 (The Pile)

Max Activating Token Index: 928

Text #7

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1889860 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1242. Min Act: -0.0000

Data Index: 106799 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1135. Min Act: -0.0000

Data Index: 1031044 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1701. Min Act: -0.0000

Data Index: 260382 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1026. Min Act: -0.0000

Data Index: 1329357 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1697. Min Act: -0.0000

Data Index: 469125 (The Pile)

Max Activating Token Index: 107

Text #13

Max Range: 1.6293. Min Range: -1.6293

Max Act: 0.9350. Min Act: -0.0000

Data Index: 193520 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1774. Min Act: -0.0000

Data Index: 121598 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1579647 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.0367. Min Act: -0.0000

Data Index: 484995 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.6293. Min Range: -1.6293

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1059282 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 1.6293. Min Range: -1.6293

Max Act: 0.9519. Min Act: -0.0000

Data Index: 502890 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 1.6293. Min Range: -1.6293

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1555137 (The Pile)

Max Activating Token Index: 280