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

Dataset: The Pile

Neuron 3787 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 475860 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2696. Min Act: -0.0000

Data Index: 337749 (The Pile)

Max Activating Token Index: 965

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1933478 (The Pile)

Max Activating Token Index: 129

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2590. Min Act: -0.0000

Data Index: 794233 (The Pile)

Max Activating Token Index: 133

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2593. Min Act: 0.0000

Data Index: 1705356 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1461082 (The Pile)

Max Activating Token Index: 148

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2409. Min Act: -0.0000

Data Index: 1515547 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2383. Min Act: -0.0000

Data Index: 968875 (The Pile)

Max Activating Token Index: 620

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2454. Min Act: -0.0000

Data Index: 831160 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2337. Min Act: -0.0000

Data Index: 477962 (The Pile)

Max Activating Token Index: 36

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2275. Min Act: -0.0000

Data Index: 447924 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2193. Min Act: 0.0000

Data Index: 1001030 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2306. Min Act: -0.0000

Data Index: 1143981 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1967113 (The Pile)

Max Activating Token Index: 1007

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1968168 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2225. Min Act: 0.0000

Data Index: 445555 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1498202 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1337142 (The Pile)

Max Activating Token Index: 158

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2177. Min Act: 0.0001

Data Index: 796965 (The Pile)

Max Activating Token Index: 59

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1747118 (The Pile)

Max Activating Token Index: 615