Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1757 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1441. Min Act: -0.0002

Data Index: 887219 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1325294 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1129353 (C4 (Web Text))

Max Activating Token Index: 173

Text #3

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1267. Min Act: -0.0002

Data Index: 856189 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1185. Min Act: -0.0002

Data Index: 310685 (C4 (Web Text))

Max Activating Token Index: 833

Text #5

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1163. Min Act: -0.0002

Data Index: 540039 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1107. Min Act: -0.0002

Data Index: 721251 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1306414 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1141. Min Act: -0.0002

Data Index: 195607 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1137. Min Act: -0.0002

Data Index: 526497 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1104. Min Act: -0.0001

Data Index: 988435 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1051. Min Act: -0.0002

Data Index: 1037573 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1031738 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1110. Min Act: -0.0002

Data Index: 279889 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1054. Min Act: -0.0002

Data Index: 776835 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1055. Min Act: -0.0002

Data Index: 468014 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1065. Min Act: -0.0002

Data Index: 551307 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1033. Min Act: -0.0001

Data Index: 60358 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1025. Min Act: -0.0002

Data Index: 461954 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1441. Min Range: -0.1441

Max Act: 0.1056. Min Act: -0.0002

Data Index: 491655 (C4 (Web Text))

Max Activating Token Index: 986