Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3740 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0933. Min Range: -1.0933

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1129293 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 1.0933. Min Range: -1.0933

Max Act: 1.0221. Min Act: -0.0001

Data Index: 858944 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.9954. Min Act: -0.0001

Data Index: 481926 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.9854. Min Act: -0.0001

Data Index: 531548 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8732. Min Act: -0.0001

Data Index: 418873 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8303. Min Act: -0.0001

Data Index: 265325 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1252263 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8606. Min Act: -0.0001

Data Index: 1123900 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8298. Min Act: -0.0001

Data Index: 270792 (C4 (Web Text))

Max Activating Token Index: 318

Text #9

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8045. Min Act: -0.0001

Data Index: 388868 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7986. Min Act: -0.0001

Data Index: 54394 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8217. Min Act: -0.0001

Data Index: 750083 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8330. Min Act: -0.0001

Data Index: 629037 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8525. Min Act: -0.0001

Data Index: 839955 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7954. Min Act: -0.0001

Data Index: 824061 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7681. Min Act: -0.0001

Data Index: 899666 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7832. Min Act: -0.0001

Data Index: 1341477 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7805. Min Act: -0.0001

Data Index: 81155 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.7676. Min Act: -0.0001

Data Index: 548643 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.0933. Min Range: -1.0933

Max Act: 0.8184. Min Act: -0.0001

Data Index: 588332 (C4 (Web Text))

Max Activating Token Index: 769