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

Dataset: The Pile

Neuron 213 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.7802. Min Act: -0.0000

Data Index: 1284780 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1694492 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1078005 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6981. Min Act: -0.0000

Data Index: 458531 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6974. Min Act: -0.0000

Data Index: 957862 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6468. Min Act: -0.0000

Data Index: 729604 (The Pile)

Max Activating Token Index: 809

Text #6

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6338. Min Act: -0.0000

Data Index: 503396 (The Pile)

Max Activating Token Index: 131

Text #7

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6441. Min Act: -0.0000

Data Index: 615119 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6233. Min Act: -0.0000

Data Index: 190864 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5801. Min Act: -0.0000

Data Index: 861984 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6008. Min Act: -0.0000

Data Index: 1202197 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1638425 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5556. Min Act: -0.0000

Data Index: 64394 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1190107 (The Pile)

Max Activating Token Index: 689

Text #14

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1357693 (The Pile)

Max Activating Token Index: 784

Text #15

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5781. Min Act: -0.0000

Data Index: 189294 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5931. Min Act: -0.0001

Data Index: 1503398 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5449. Min Act: -0.0000

Data Index: 1555014 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5834. Min Act: -0.0000

Data Index: 60540 (The Pile)

Max Activating Token Index: 758

Text #19

Max Range: 0.7802. Min Range: -0.7802

Max Act: 0.5870. Min Act: -0.0000

Data Index: 345451 (The Pile)

Max Activating Token Index: 677