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

Dataset: The Pile

Neuron 2169 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4352. Min Range: -1.4352

Max Act: 1.4352. Min Act: -0.0000

Data Index: 738617 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.9683. Min Act: -0.0000

Data Index: 546567 (The Pile)

Max Activating Token Index: 91

Text #2

Max Range: 1.4352. Min Range: -1.4352

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1163642 (The Pile)

Max Activating Token Index: 363

Text #3

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1372075 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1300855 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.9466. Min Act: -0.0000

Data Index: 1099107 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8921. Min Act: -0.0000

Data Index: 1703931 (The Pile)

Max Activating Token Index: 148

Text #7

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.9642. Min Act: -0.0000

Data Index: 236586 (The Pile)

Max Activating Token Index: 108

Text #8

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1226843 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1808398 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8743. Min Act: -0.0000

Data Index: 909209 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8568. Min Act: -0.0000

Data Index: 427435 (The Pile)

Max Activating Token Index: 87

Text #12

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1479145 (The Pile)

Max Activating Token Index: 78

Text #13

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8407. Min Act: -0.0000

Data Index: 354703 (The Pile)

Max Activating Token Index: 189

Text #14

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1358635 (The Pile)

Max Activating Token Index: 67

Text #15

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8647. Min Act: -0.0000

Data Index: 457011 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1045128 (The Pile)

Max Activating Token Index: 18

Text #17

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.8440. Min Act: -0.0000

Data Index: 668110 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.7764. Min Act: -0.0000

Data Index: 269186 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.4352. Min Range: -1.4352

Max Act: 0.7511. Min Act: -0.0000

Data Index: 989323 (The Pile)

Max Activating Token Index: 742