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

Dataset: The Pile

Neuron 2201 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: 0.7395. Min Range: -0.7395

Max Act: 0.7395. Min Act: -0.0000

Data Index: 1213167 (The Pile)

Max Activating Token Index: 110

Text #1

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1789936 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.6136. Min Act: -0.0000

Data Index: 196756 (The Pile)

Max Activating Token Index: 911

Text #3

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5756. Min Act: -0.0000

Data Index: 109025 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1605047 (The Pile)

Max Activating Token Index: 718

Text #5

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1211584 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1591707 (The Pile)

Max Activating Token Index: 666

Text #7

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1950407 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1977536 (The Pile)

Max Activating Token Index: 22

Text #9

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5401. Min Act: -0.0000

Data Index: 1415002 (The Pile)

Max Activating Token Index: 737

Text #10

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5948. Min Act: -0.0000

Data Index: 822667 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1934945 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1945981 (The Pile)

Max Activating Token Index: 467

Text #13

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5950. Min Act: -0.0000

Data Index: 1352835 (The Pile)

Max Activating Token Index: 269

Text #14

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1808934 (The Pile)

Max Activating Token Index: 963

Text #15

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5177. Min Act: -0.0000

Data Index: 43819 (The Pile)

Max Activating Token Index: 248

Text #16

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5112. Min Act: -0.0000

Data Index: 97958 (The Pile)

Max Activating Token Index: 857

Text #17

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1291216 (The Pile)

Max Activating Token Index: 139

Text #18

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5316. Min Act: -0.0000

Data Index: 432480 (The Pile)

Max Activating Token Index: 556

Text #19

Max Range: 0.7395. Min Range: -0.7395

Max Act: 0.5895. Min Act: -0.0000

Data Index: 772433 (The Pile)

Max Activating Token Index: 857