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

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

Neuron 2248 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.5188. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.5276. Min Act: -0.0000

Data Index: 195086 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.2564. Min Act: -0.0000

Data Index: 1178360 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1317882 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.1397. Min Act: -0.0000

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0758. Min Act: -0.0000

Data Index: 587580 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0689. Min Act: -0.0000

Data Index: 1236571 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0006. Min Act: 0.0000

Data Index: 970492 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9987. Min Act: -0.0000

Data Index: 556259 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1002071 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9823. Min Act: -0.0000

Data Index: 460419 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9878. Min Act: -0.0000

Data Index: 764162 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9121. Min Act: 0.0000

Data Index: 664096 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9677. Min Act: -0.0000

Data Index: 1022336 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 1.5276. Min Range: -1.5276

Max Act: 1.0407. Min Act: -0.0000

Data Index: 852081 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1249200 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1328909 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9907. Min Act: -0.0000

Data Index: 708630 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9355. Min Act: -0.0000

Data Index: 260755 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.5276. Min Range: -1.5276

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1331593 (C4 (Web Text))

Max Activating Token Index: 903