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

Dataset: The Pile

Neuron 310 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1438216 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1850095 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7782. Min Act: -0.0000

Data Index: 731715 (The Pile)

Max Activating Token Index: 669

Text #3

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7718. Min Act: -0.0000

Data Index: 684156 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7197. Min Act: -0.0000

Data Index: 450960 (The Pile)

Max Activating Token Index: 553

Text #5

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7022. Min Act: -0.0000

Data Index: 988945 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7617. Min Act: -0.0000

Data Index: 1439893 (The Pile)

Max Activating Token Index: 495

Text #7

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7348. Min Act: -0.0000

Data Index: 454067 (The Pile)

Max Activating Token Index: 459

Text #8

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6867. Min Act: -0.0000

Data Index: 1255245 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1542440 (The Pile)

Max Activating Token Index: 668

Text #10

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6392. Min Act: -0.0000

Data Index: 1988495 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1502293 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6743. Min Act: -0.0000

Data Index: 335844 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7621. Min Act: -0.0000

Data Index: 1141220 (The Pile)

Max Activating Token Index: 119

Text #14

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1281332 (The Pile)

Max Activating Token Index: 647

Text #15

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7504. Min Act: -0.0000

Data Index: 226168 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1838010 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7271. Min Act: -0.0000

Data Index: 196318 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1399937 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1492105 (The Pile)

Max Activating Token Index: 881