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

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

Neuron 3014 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: 0.3194. Min Range: -0.3194

Max Act: 0.3194. Min Act: -0.0001

Data Index: 172746 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2828. Min Act: -0.0001

Data Index: 343603 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2730. Min Act: -0.0001

Data Index: 599331 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2478. Min Act: -0.0001

Data Index: 711804 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2588. Min Act: -0.0001

Data Index: 313228 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2646. Min Act: -0.0001

Data Index: 20590 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2550. Min Act: -0.0001

Data Index: 305121 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2341. Min Act: -0.0001

Data Index: 545557 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2437. Min Act: -0.0001

Data Index: 863853 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2348. Min Act: -0.0001

Data Index: 239138 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2352. Min Act: -0.0001

Data Index: 33110 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2567. Min Act: -0.0001

Data Index: 488444 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2195. Min Act: -0.0001

Data Index: 509137 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2239. Min Act: -0.0001

Data Index: 862271 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1047524 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2207. Min Act: -0.0001

Data Index: 1111922 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2053. Min Act: -0.0001

Data Index: 975059 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.1922. Min Act: -0.0001

Data Index: 430308 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2174. Min Act: -0.0001

Data Index: 233527 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.3194. Min Range: -0.3194

Max Act: 0.2127. Min Act: -0.0001

Data Index: 1347953 (C4 (Web Text))

Max Activating Token Index: 236