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

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

Neuron 1794 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0001

Data Index: 480322 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1243. Min Act: -0.0001

Data Index: 440346 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1209. Min Act: -0.0001

Data Index: 934146 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1191. Min Act: -0.0001

Data Index: 878419 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1139. Min Act: -0.0001

Data Index: 857158 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1162. Min Act: -0.0001

Data Index: 352371 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1099. Min Act: -0.0001

Data Index: 749993 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1084. Min Act: -0.0001

Data Index: 13103 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1078. Min Act: -0.0001

Data Index: 156117 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1066. Min Act: -0.0001

Data Index: 150936 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1022. Min Act: -0.0001

Data Index: 149317 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1077. Min Act: -0.0001

Data Index: 991268 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1206397 (C4 (Web Text))

Max Activating Token Index: 5

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0983. Min Act: -0.0001

Data Index: 983049 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1070583 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0992. Min Act: -0.0001

Data Index: 189351 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0983. Min Act: -0.0001

Data Index: 1341882 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0978. Min Act: -0.0001

Data Index: 495266 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0950. Min Act: -0.0001

Data Index: 208545 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1072945 (C4 (Web Text))

Max Activating Token Index: 146