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

Dataset: The Pile

Neuron 2900 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: 1.1302. Min Range: -1.1302

Max Act: 1.1302. Min Act: -0.0000

Data Index: 411715 (The Pile)

Max Activating Token Index: 253

Text #1

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.9044. Min Act: -0.0000

Data Index: 342276 (The Pile)

Max Activating Token Index: 94

Text #2

Max Range: 1.1302. Min Range: -1.1302

Max Act: 1.0233. Min Act: -0.0000

Data Index: 745304 (The Pile)

Max Activating Token Index: 255

Text #3

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8835. Min Act: -0.0000

Data Index: 557891 (The Pile)

Max Activating Token Index: 170

Text #4

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1761891 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1640499 (The Pile)

Max Activating Token Index: 595

Text #6

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1561523 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6765. Min Act: -0.0000

Data Index: 789078 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7805. Min Act: -0.0000

Data Index: 212219 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6728. Min Act: -0.0000

Data Index: 1620886 (The Pile)

Max Activating Token Index: 513

Text #10

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7918. Min Act: -0.0000

Data Index: 106491 (The Pile)

Max Activating Token Index: 983

Text #11

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.7085. Min Act: -0.0000

Data Index: 530798 (The Pile)

Max Activating Token Index: 274

Text #12

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1544702 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6698. Min Act: -0.0000

Data Index: 618115 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1413641 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1102686 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1878721 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6032. Min Act: -0.0000

Data Index: 988098 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1033148 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.1302. Min Range: -1.1302

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1214710 (The Pile)

Max Activating Token Index: 965