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

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

Neuron 1440 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.5528. Min Act: -0.0000

Data Index: 967847 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.6894. Min Act: -0.0000

Data Index: 1181828 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.6992. Min Act: -0.0000

Data Index: 774595 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.8462. Min Act: -0.0000

Data Index: 613551 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.9070. Min Act: -0.0001

Data Index: 679170 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 2.8462. Min Range: -2.8462

Max Act: 2.0281. Min Act: -0.0001

Data Index: 962605 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.8165. Min Act: -0.0001

Data Index: 947601 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.9006. Min Act: -0.0000

Data Index: 692687 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7956. Min Act: -0.0000

Data Index: 172380 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7930. Min Act: -0.0001

Data Index: 1337806 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1148930 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.6368. Min Act: -0.0001

Data Index: 738248 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.8188. Min Act: -0.0000

Data Index: 851502 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.6379. Min Act: -0.0000

Data Index: 295730 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7269. Min Act: -0.0000

Data Index: 215786 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.8162. Min Act: -0.0000

Data Index: 705805 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7183. Min Act: -0.0001

Data Index: 151480 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.8109. Min Act: -0.0000

Data Index: 994971 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.8173. Min Act: -0.0001

Data Index: 472310 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 2.8462. Min Range: -2.8462

Max Act: 1.7961. Min Act: -0.0000

Data Index: 614094 (C4 (Web Text))

Max Activating Token Index: 350