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

Dataset: The Pile

Neuron 3183 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: 0.6243. Min Range: -0.6243

Max Act: 0.6243. Min Act: -0.0000

Data Index: 195606 (The Pile)

Max Activating Token Index: 797

Text #1

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.5507. Min Act: -0.0000

Data Index: 1073062 (The Pile)

Max Activating Token Index: 609

Text #2

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.6072. Min Act: -0.0000

Data Index: 795640 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.6125. Min Act: -0.0000

Data Index: 1755956 (The Pile)

Max Activating Token Index: 536

Text #4

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.6172. Min Act: -0.0000

Data Index: 189146 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.5396. Min Act: -0.0000

Data Index: 966627 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1987737 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1810757 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.5043. Min Act: -0.0000

Data Index: 803836 (The Pile)

Max Activating Token Index: 963

Text #9

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4798. Min Act: -0.0000

Data Index: 783293 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4594. Min Act: -0.0000

Data Index: 578452 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4919. Min Act: -0.0000

Data Index: 206366 (The Pile)

Max Activating Token Index: 434

Text #12

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4298. Min Act: -0.0000

Data Index: 716822 (The Pile)

Max Activating Token Index: 480

Text #13

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4529. Min Act: -0.0000

Data Index: 1795638 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4437. Min Act: -0.0000

Data Index: 841542 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4690. Min Act: -0.0000

Data Index: 1532312 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4298. Min Act: -0.0000

Data Index: 884628 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4556. Min Act: -0.0000

Data Index: 841510 (The Pile)

Max Activating Token Index: 614

Text #18

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4378. Min Act: -0.0000

Data Index: 638053 (The Pile)

Max Activating Token Index: 879

Text #19

Max Range: 0.6243. Min Range: -0.6243

Max Act: 0.4661. Min Act: -0.0000

Data Index: 1290249 (The Pile)

Max Activating Token Index: 255