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

Dataset: The Pile

Neuron 3128 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: 4.4158. Min Range: -4.4158

Max Act: 4.4158. Min Act: -0.0000

Data Index: 1479271 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 4.4158. Min Range: -4.4158

Max Act: 4.2419. Min Act: -0.0000

Data Index: 1459905 (The Pile)

Max Activating Token Index: 707

Text #2

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.6709. Min Act: -0.0000

Data Index: 907076 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.5141. Min Act: -0.0000

Data Index: 227286 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.4059. Min Act: -0.0000

Data Index: 983975 (The Pile)

Max Activating Token Index: 698

Text #5

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.6568. Min Act: -0.0000

Data Index: 496481 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.3765. Min Act: -0.0000

Data Index: 372024 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.2529. Min Act: -0.0000

Data Index: 202816 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 4.4158. Min Range: -4.4158

Max Act: 2.8466. Min Act: -0.0000

Data Index: 1258963 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.2408. Min Act: -0.0000

Data Index: 828560 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.3449. Min Act: -0.0000

Data Index: 917011 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.0466. Min Act: -0.0000

Data Index: 1861278 (The Pile)

Max Activating Token Index: 841

Text #12

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.1819. Min Act: -0.0000

Data Index: 733161 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.2663. Min Act: -0.0000

Data Index: 1748988 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.1923. Min Act: -0.0000

Data Index: 1675172 (The Pile)

Max Activating Token Index: 947

Text #15

Max Range: 4.4158. Min Range: -4.4158

Max Act: 2.9565. Min Act: -0.0000

Data Index: 653267 (The Pile)

Max Activating Token Index: 900

Text #16

Max Range: 4.4158. Min Range: -4.4158

Max Act: 2.5526. Min Act: -0.0000

Data Index: 1093745 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 4.4158. Min Range: -4.4158

Max Act: 2.8437. Min Act: -0.0000

Data Index: 1016557 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 4.4158. Min Range: -4.4158

Max Act: 2.7604. Min Act: -0.0000

Data Index: 1061805 (The Pile)

Max Activating Token Index: 902

Text #19

Max Range: 4.4158. Min Range: -4.4158

Max Act: 3.3477. Min Act: -0.0000

Data Index: 1705985 (The Pile)

Max Activating Token Index: 614