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

Dataset: The Pile

Neuron 1411 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.8254. Min Act: -0.0000

Data Index: 1624376 (The Pile)

Max Activating Token Index: 613

Text #1

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.8193. Min Act: -0.0000

Data Index: 645423 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.7061. Min Act: -0.0000

Data Index: 1330208 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1103702 (The Pile)

Max Activating Token Index: 54

Text #4

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1681967 (The Pile)

Max Activating Token Index: 953

Text #5

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.6486. Min Act: -0.0000

Data Index: 950062 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1590992 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5321. Min Act: -0.0000

Data Index: 777076 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5200. Min Act: -0.0000

Data Index: 982209 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.6492. Min Act: -0.0000

Data Index: 1389765 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4733. Min Act: -0.0000

Data Index: 331995 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1197586 (The Pile)

Max Activating Token Index: 60

Text #12

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1381917 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4968. Min Act: -0.0000

Data Index: 443842 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4626. Min Act: -0.0000

Data Index: 897484 (The Pile)

Max Activating Token Index: 930

Text #15

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5530. Min Act: -0.0000

Data Index: 957042 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4905. Min Act: -0.0000

Data Index: 1204552 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1797258 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.4214. Min Act: -0.0000

Data Index: 237645 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 1.8254. Min Range: -1.8254

Max Act: 1.5312. Min Act: -0.0000

Data Index: 1771462 (The Pile)

Max Activating Token Index: 871