Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2881 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0001

Data Index: 624916 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0183. Min Act: -0.0001

Data Index: 1158613 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0181. Min Act: -0.0001

Data Index: 812152 (C4 (Web Text))

Max Activating Token Index: 239

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0186. Min Act: -0.0001

Data Index: 544821 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0178. Min Act: -0.0001

Data Index: 867373 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0191. Min Act: -0.0001

Data Index: 1124036 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0182. Min Act: -0.0001

Data Index: 287697 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0164. Min Act: -0.0001

Data Index: 1058027 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0174. Min Act: -0.0001

Data Index: 845345 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0142. Min Act: -0.0001

Data Index: 1528687 (Python Code)

Max Activating Token Index: 865

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0159. Min Act: -0.0001

Data Index: 950536 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0180. Min Act: -0.0001

Data Index: 1143567 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0167. Min Act: -0.0001

Data Index: 593429 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0162. Min Act: -0.0001

Data Index: 916515 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0157. Min Act: -0.0001

Data Index: 403237 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0161. Min Act: -0.0001

Data Index: 367779 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0169. Min Act: -0.0001

Data Index: 703111 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0148. Min Act: -0.0001

Data Index: 392095 (C4 (Web Text))

Max Activating Token Index: 898

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0159. Min Act: -0.0001

Data Index: 200201 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0134. Min Act: -0.0001

Data Index: 973435 (C4 (Web Text))

Max Activating Token Index: 911