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

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

Neuron 4735 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.3205. Min Act: -0.0000

Data Index: 243873 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.3275. Min Act: -0.0000

Data Index: 826051 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0777. Min Act: -0.0000

Data Index: 264835 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.1432. Min Act: -0.0001

Data Index: 948421 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0739. Min Act: -0.0000

Data Index: 803270 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0880. Min Act: -0.0001

Data Index: 571042 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0488. Min Act: -0.0000

Data Index: 1125834 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0462. Min Act: -0.0000

Data Index: 239008 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0571. Min Act: -0.0000

Data Index: 736096 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0419. Min Act: -0.0000

Data Index: 137064 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0782. Min Act: -0.0001

Data Index: 1195359 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9478. Min Act: -0.0000

Data Index: 313475 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1007688 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0112. Min Act: -0.0000

Data Index: 796067 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9791. Min Act: -0.0000

Data Index: 703070 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9729. Min Act: -0.0000

Data Index: 195117 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 1.3275. Min Range: -1.3275

Max Act: 1.0628. Min Act: -0.0000

Data Index: 546200 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9263. Min Act: -0.0001

Data Index: 330844 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9450. Min Act: -0.0000

Data Index: 1648779 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 1.3275. Min Range: -1.3275

Max Act: 0.9065. Min Act: -0.0001

Data Index: 1133444 (C4 (Web Text))

Max Activating Token Index: 41