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

Dataset: The Pile

Neuron 1775 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: 0.9926. Min Range: -0.9926

Max Act: 0.9926. Min Act: -0.0000

Data Index: 1676028 (The Pile)

Max Activating Token Index: 404

Text #1

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8826. Min Act: -0.0000

Data Index: 794264 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1171098 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.9192. Min Act: -0.0000

Data Index: 1132903 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.9005. Min Act: -0.0000

Data Index: 961772 (The Pile)

Max Activating Token Index: 984

Text #5

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8432. Min Act: -0.0000

Data Index: 1381491 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.9231. Min Act: -0.0000

Data Index: 667580 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8929. Min Act: -0.0000

Data Index: 438702 (The Pile)

Max Activating Token Index: 964

Text #8

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8171. Min Act: 0.0000

Data Index: 985942 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8416. Min Act: 0.0000

Data Index: 989550 (The Pile)

Max Activating Token Index: 119

Text #10

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1389790 (The Pile)

Max Activating Token Index: 239

Text #11

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8252. Min Act: -0.0000

Data Index: 695445 (The Pile)

Max Activating Token Index: 948

Text #12

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8244. Min Act: -0.0000

Data Index: 370094 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1174059 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1290931 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1550591 (The Pile)

Max Activating Token Index: 549

Text #16

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8152. Min Act: 0.0000

Data Index: 1066206 (The Pile)

Max Activating Token Index: 933

Text #17

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1912623 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8310. Min Act: -0.0000

Data Index: 36246 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.9926. Min Range: -0.9926

Max Act: 0.8300. Min Act: 0.0000

Data Index: 101598 (The Pile)

Max Activating Token Index: 191