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

Dataset: The Pile

Neuron 1185 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: 1.6583. Min Range: -1.6583

Max Act: 1.6516. Min Act: -0.0000

Data Index: 336041 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.5957. Min Act: -0.0000

Data Index: 1740885 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.6583. Min Act: -0.0000

Data Index: 1673196 (The Pile)

Max Activating Token Index: 937

Text #3

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.6125. Min Act: -0.0000

Data Index: 1017800 (The Pile)

Max Activating Token Index: 177

Text #4

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.5548. Min Act: -0.0000

Data Index: 802969 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.4423. Min Act: -0.0000

Data Index: 381846 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1068483 (The Pile)

Max Activating Token Index: 345

Text #7

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.4267. Min Act: -0.0000

Data Index: 652345 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.4590. Min Act: -0.0000

Data Index: 1327880 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.5506. Min Act: -0.0000

Data Index: 1454573 (The Pile)

Max Activating Token Index: 412

Text #10

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.4593. Min Act: -0.0000

Data Index: 679297 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1507030 (The Pile)

Max Activating Token Index: 218

Text #12

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.6067. Min Act: -0.0000

Data Index: 1095746 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.3044. Min Act: -0.0000

Data Index: 1780270 (The Pile)

Max Activating Token Index: 488

Text #14

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.3769. Min Act: -0.0000

Data Index: 240548 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.3439. Min Act: -0.0000

Data Index: 828141 (The Pile)

Max Activating Token Index: 654

Text #16

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.3406. Min Act: -0.0000

Data Index: 642362 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.2718. Min Act: -0.0000

Data Index: 1036544 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1723814 (The Pile)

Max Activating Token Index: 243

Text #19

Max Range: 1.6583. Min Range: -1.6583

Max Act: 1.2590. Min Act: -0.0000

Data Index: 1025670 (The Pile)

Max Activating Token Index: 387