Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 655 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1280. Min Act: -0.0002

Data Index: 923673 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1218. Min Act: -0.0002

Data Index: 126796 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1197. Min Act: -0.0002

Data Index: 248103 (C4 (Web Text))

Max Activating Token Index: 168

Text #3

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1161. Min Act: -0.0002

Data Index: 767581 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1229. Min Act: -0.0002

Data Index: 185004 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1137. Min Act: -0.0002

Data Index: 398678 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1130. Min Act: -0.0002

Data Index: 692536 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1191. Min Act: -0.0002

Data Index: 61547 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1087. Min Act: -0.0002

Data Index: 469725 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1124. Min Act: -0.0002

Data Index: 236119 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1085. Min Act: -0.0002

Data Index: 351210 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0975. Min Act: -0.0002

Data Index: 390260 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1017. Min Act: -0.0002

Data Index: 889593 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1166. Min Act: -0.0002

Data Index: 858226 (C4 (Web Text))

Max Activating Token Index: 400

Text #14

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.0942. Min Act: -0.0002

Data Index: 343309 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1182. Min Act: -0.0002

Data Index: 638079 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1064. Min Act: -0.0002

Data Index: 695042 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1105. Min Act: -0.0002

Data Index: 441555 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1089. Min Act: -0.0002

Data Index: 728227 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.1280. Min Range: -0.1280

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1195524 (C4 (Web Text))

Max Activating Token Index: 476