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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3443 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0995. Min Range: -1.0995

Max Act: 1.0995. Min Act: 0.0000

Data Index: 197010 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1017621 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8931. Min Act: -0.0001

Data Index: 947180 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9152. Min Act: -0.0001

Data Index: 1161049 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8844. Min Act: -0.0000

Data Index: 518571 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.9042. Min Act: -0.0000

Data Index: 878434 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8486. Min Act: -0.0000

Data Index: 78405 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.8590. Min Act: -0.0001

Data Index: 748997 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7203. Min Act: -0.0001

Data Index: 924271 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7171. Min Act: -0.0000

Data Index: 892058 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7439. Min Act: -0.0000

Data Index: 431037 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1183854 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7250. Min Act: -0.0000

Data Index: 303237 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7055. Min Act: -0.0001

Data Index: 1272490 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7192. Min Act: -0.0001

Data Index: 1310537 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.6961. Min Act: -0.0000

Data Index: 779837 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.6896. Min Act: -0.0000

Data Index: 305542 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7061. Min Act: -0.0000

Data Index: 20371 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.7034. Min Act: 0.0000

Data Index: 20450 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.0995. Min Range: -1.0995

Max Act: 0.6985. Min Act: 0.0001

Data Index: 873883 (C4 (Web Text))

Max Activating Token Index: 761