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

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

Neuron 5996 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.4080. Min Act: -0.0001

Data Index: 636223 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.2203. Min Act: -0.0001

Data Index: 978595 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.1050. Min Act: -0.0001

Data Index: 1090028 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.0593. Min Act: -0.0001

Data Index: 862375 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.1109. Min Act: -0.0001

Data Index: 475830 (C4 (Web Text))

Max Activating Token Index: 398

Text #5

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.0395. Min Act: -0.0001

Data Index: 1208216 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9334. Min Act: -0.0001

Data Index: 1137053 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9932. Min Act: -0.0001

Data Index: 242164 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9327. Min Act: -0.0001

Data Index: 697590 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9095. Min Act: -0.0001

Data Index: 772749 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8844. Min Act: -0.0001

Data Index: 1021932 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9188. Min Act: -0.0001

Data Index: 915600 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9226. Min Act: -0.0001

Data Index: 1167230 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9204. Min Act: -0.0001

Data Index: 180583 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8115. Min Act: -0.0001

Data Index: 663209 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8578. Min Act: -0.0001

Data Index: 955868 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8798. Min Act: -0.0001

Data Index: 121069 (C4 (Web Text))

Max Activating Token Index: 391

Text #17

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8462. Min Act: -0.0001

Data Index: 544111 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9239. Min Act: -0.0001

Data Index: 1040007 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8421. Min Act: -0.0001

Data Index: 933365 (C4 (Web Text))

Max Activating Token Index: 698