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

Dataset: The Pile

Neuron 3629 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.4319. Min Act: -0.0000

Data Index: 975101 (The Pile)

Max Activating Token Index: 295

Text #1

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1996597 (The Pile)

Max Activating Token Index: 163

Text #2

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.2546. Min Act: -0.0000

Data Index: 1341342 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.1003. Min Act: -0.0000

Data Index: 1619268 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.0909. Min Act: -0.0000

Data Index: 676919 (The Pile)

Max Activating Token Index: 1010

Text #5

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.1619. Min Act: -0.0000

Data Index: 516419 (The Pile)

Max Activating Token Index: 967

Text #6

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.0494. Min Act: -0.0000

Data Index: 1520074 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.0304. Min Act: -0.0000

Data Index: 619343 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9726. Min Act: -0.0000

Data Index: 853130 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9162. Min Act: -0.0000

Data Index: 714165 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.4319. Min Range: -1.4319

Max Act: 1.0018. Min Act: -0.0000

Data Index: 844095 (The Pile)

Max Activating Token Index: 250

Text #11

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.8646. Min Act: -0.0000

Data Index: 785959 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9146. Min Act: -0.0000

Data Index: 1522932 (The Pile)

Max Activating Token Index: 540

Text #13

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9914. Min Act: -0.0000

Data Index: 899640 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9693. Min Act: -0.0000

Data Index: 785684 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.7544. Min Act: -0.0000

Data Index: 558256 (The Pile)

Max Activating Token Index: 885

Text #16

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9395. Min Act: -0.0000

Data Index: 120372 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1520357 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.8719. Min Act: -0.0000

Data Index: 1197051 (The Pile)

Max Activating Token Index: 724

Text #19

Max Range: 1.4319. Min Range: -1.4319

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1306237 (The Pile)

Max Activating Token Index: 141