Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1059 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.8104. Min Act: -0.0000

Data Index: 769216 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.4665. Min Act: -0.0000

Data Index: 398708 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.1147. Min Act: -0.0000

Data Index: 1042943 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.1365. Min Act: -0.0000

Data Index: 1335541 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.0489. Min Act: -0.0000

Data Index: 975300 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.2984. Min Act: -0.0000

Data Index: 925269 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 4.8104. Min Range: -4.8104

Max Act: 4.1225. Min Act: -0.0000

Data Index: 831440 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.9467. Min Act: -0.0000

Data Index: 265498 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.8919. Min Act: -0.0000

Data Index: 1125748 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.9569. Min Act: -0.0000

Data Index: 991020 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.8518. Min Act: -0.0000

Data Index: 485273 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.6414. Min Act: -0.0000

Data Index: 858104 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.8036. Min Act: -0.0000

Data Index: 449232 (C4 (Web Text))

Max Activating Token Index: 888

Text #13

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.7721. Min Act: -0.0000

Data Index: 810497 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.9267. Min Act: -0.0000

Data Index: 1053807 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.7223. Min Act: -0.0000

Data Index: 736103 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.5592. Min Act: -0.0000

Data Index: 434216 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.8169. Min Act: -0.0000

Data Index: 1187100 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.5453. Min Act: -0.0000

Data Index: 1073321 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 4.8104. Min Range: -4.8104

Max Act: 3.7808. Min Act: -0.0000

Data Index: 1210091 (C4 (Web Text))

Max Activating Token Index: 467