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

Dataset: The Pile

Neuron 3360 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0951. Min Act: -0.0000

Data Index: 1331343 (The Pile)

Max Activating Token Index: 635

Text #1

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0313. Min Act: -0.0000

Data Index: 158936 (The Pile)

Max Activating Token Index: 409

Text #2

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0554. Min Act: -0.0000

Data Index: 698958 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9802. Min Act: -0.0000

Data Index: 1330791 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1342314 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1631820 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9196. Min Act: -0.0000

Data Index: 948572 (The Pile)

Max Activating Token Index: 32

Text #7

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9635. Min Act: -0.0000

Data Index: 475425 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 1.0951. Min Range: -1.0951

Max Act: 1.0935. Min Act: -0.0000

Data Index: 1814069 (The Pile)

Max Activating Token Index: 874

Text #9

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9656. Min Act: -0.0000

Data Index: 809591 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9201. Min Act: -0.0000

Data Index: 294119 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1328216 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9327. Min Act: -0.0000

Data Index: 997760 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.7760. Min Act: -0.0000

Data Index: 317090 (The Pile)

Max Activating Token Index: 1004

Text #14

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1344692 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1159217 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1512868 (The Pile)

Max Activating Token Index: 168

Text #17

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1830590 (The Pile)

Max Activating Token Index: 366

Text #18

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8641. Min Act: -0.0000

Data Index: 55742 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.0951. Min Range: -1.0951

Max Act: 0.8214. Min Act: -0.0000

Data Index: 893371 (The Pile)

Max Activating Token Index: 847