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

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

Neuron 3874 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1654. Min Act: -0.0001

Data Index: 939046 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1282 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1191. Min Act: -0.0001

Data Index: 8743 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1225. Min Act: -0.0001

Data Index: 863473 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1249. Min Act: -0.0001

Data Index: 657965 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1147. Min Act: -0.0001

Data Index: 796593 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1297. Min Act: -0.0001

Data Index: 928159 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1161. Min Act: -0.0001

Data Index: 891002 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1310374 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1082. Min Act: -0.0001

Data Index: 316898 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1153. Min Act: -0.0001

Data Index: 29056 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.0864. Min Act: -0.0001

Data Index: 12323 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1108. Min Act: -0.0001

Data Index: 1167655 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1183. Min Act: -0.0001

Data Index: 334535 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1093. Min Act: -0.0001

Data Index: 545174 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1107. Min Act: -0.0001

Data Index: 1308514 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.0990. Min Act: -0.0001

Data Index: 866342 (C4 (Web Text))

Max Activating Token Index: 469

Text #17

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.0931. Min Act: -0.0001

Data Index: 639740 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.0971. Min Act: -0.0001

Data Index: 421262 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.0952. Min Act: -0.0001

Data Index: 720466 (C4 (Web Text))

Max Activating Token Index: 666