Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5131 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.7602. Min Act: -0.0000

Data Index: 669457 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1116464 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.3223. Min Act: -0.0000

Data Index: 553432 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.1682. Min Act: -0.0000

Data Index: 312795 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.2259. Min Act: -0.0000

Data Index: 683551 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0832. Min Act: -0.0000

Data Index: 167510 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.9887. Min Act: -0.0000

Data Index: 307061 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0369. Min Act: -0.0000

Data Index: 532259 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0189. Min Act: -0.0000

Data Index: 623074 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.9591. Min Act: -0.0000

Data Index: 408875 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1249992 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 1.7602. Min Range: -1.7602

Max Act: 1.0073. Min Act: -0.0000

Data Index: 712606 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.9257. Min Act: -0.0000

Data Index: 29764 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8883. Min Act: -0.0000

Data Index: 937735 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1288773 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8755. Min Act: -0.0000

Data Index: 1302527 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8778. Min Act: -0.0000

Data Index: 652464 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8703. Min Act: -0.0000

Data Index: 802773 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.9212. Min Act: -0.0000

Data Index: 814149 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 1.7602. Min Range: -1.7602

Max Act: 0.8648. Min Act: -0.0000

Data Index: 809455 (C4 (Web Text))

Max Activating Token Index: 741