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

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

Neuron 3634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.6405. Min Act: -0.0001

Data Index: 604041 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.6809. Min Act: -0.0001

Data Index: 91187 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.5643. Min Act: -0.0001

Data Index: 300749 (C4 (Web Text))

Max Activating Token Index: 498

Text #3

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.3967. Min Act: -0.0001

Data Index: 717112 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.4290. Min Act: -0.0001

Data Index: 862793 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.4541. Min Act: -0.0001

Data Index: 695123 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.4738. Min Act: -0.0001

Data Index: 458932 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.3363. Min Act: -0.0001

Data Index: 794296 (C4 (Web Text))

Max Activating Token Index: 686

Text #8

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.3179. Min Act: -0.0001

Data Index: 651189 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2823. Min Act: -0.0001

Data Index: 624710 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2878. Min Act: -0.0001

Data Index: 963799 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.3737. Min Act: -0.0001

Data Index: 1078933 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2262. Min Act: -0.0001

Data Index: 784112 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2828. Min Act: -0.0001

Data Index: 873357 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2118. Min Act: -0.0001

Data Index: 440119 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2071. Min Act: -0.0001

Data Index: 1223563 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.2307. Min Act: -0.0001

Data Index: 632636 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.1585. Min Act: -0.0001

Data Index: 171019 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.1407. Min Act: -0.0001

Data Index: 1356434 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 1.6809. Min Range: -1.6809

Max Act: 1.0449. Min Act: -0.0001

Data Index: 13843 (C4 (Web Text))

Max Activating Token Index: 378