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

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

Neuron 5494 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1481. Min Act: -0.0002

Data Index: 1161013 (C4 (Web Text))

Max Activating Token Index: 563

Text #1

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1278. Min Act: -0.0002

Data Index: 626150 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1219. Min Act: -0.0003

Data Index: 708799 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1173. Min Act: -0.0003

Data Index: 246555 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1174. Min Act: -0.0002

Data Index: 401571 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1169. Min Act: -0.0002

Data Index: 1175160 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1009605 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1155. Min Act: -0.0002

Data Index: 291132 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1151. Min Act: -0.0002

Data Index: 646717 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1113. Min Act: -0.0002

Data Index: 390750 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1144. Min Act: -0.0002

Data Index: 1091970 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1118. Min Act: -0.0002

Data Index: 97023 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1138. Min Act: -0.0002

Data Index: 869829 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1109. Min Act: -0.0002

Data Index: 1182715 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1138800 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1081. Min Act: -0.0002

Data Index: 299456 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1062. Min Act: -0.0002

Data Index: 1305112 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1122867 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1095. Min Act: -0.0002

Data Index: 714254 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1086. Min Act: -0.0002

Data Index: 931194 (C4 (Web Text))

Max Activating Token Index: 863