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

Dataset: The Pile

Neuron 2300 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: 1.0815. Min Range: -1.0815

Max Act: 1.0815. Min Act: -0.0000

Data Index: 91829 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9865. Min Act: -0.0000

Data Index: 940478 (The Pile)

Max Activating Token Index: 359

Text #2

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1009614 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9786. Min Act: -0.0000

Data Index: 313383 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8896. Min Act: -0.0000

Data Index: 470475 (The Pile)

Max Activating Token Index: 568

Text #5

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1535369 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1772962 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7921. Min Act: -0.0000

Data Index: 709956 (The Pile)

Max Activating Token Index: 741

Text #8

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1778465 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8301. Min Act: -0.0000

Data Index: 1430350 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.8289. Min Act: -0.0000

Data Index: 575402 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7595. Min Act: -0.0000

Data Index: 172306 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1250479 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1152143 (The Pile)

Max Activating Token Index: 513

Text #14

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1512109 (The Pile)

Max Activating Token Index: 216

Text #15

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1787498 (The Pile)

Max Activating Token Index: 105

Text #16

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6968. Min Act: -0.0000

Data Index: 245643 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7406. Min Act: -0.0000

Data Index: 913028 (The Pile)

Max Activating Token Index: 7

Text #18

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.7380. Min Act: -0.0000

Data Index: 654220 (The Pile)

Max Activating Token Index: 393

Text #19

Max Range: 1.0815. Min Range: -1.0815

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1353028 (The Pile)

Max Activating Token Index: 975