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

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

Neuron 3318 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: 1.9699. Min Range: -1.9699

Max Act: 1.8097. Min Act: -0.0001

Data Index: 540748 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.9699. Min Act: -0.0001

Data Index: 640468 (C4 (Web Text))

Max Activating Token Index: 842

Text #2

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.5250. Min Act: -0.0001

Data Index: 643073 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.5922. Min Act: -0.0001

Data Index: 59837 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.5552. Min Act: -0.0001

Data Index: 945008 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.4597. Min Act: -0.0001

Data Index: 611835 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.4440. Min Act: -0.0001

Data Index: 879214 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.3549. Min Act: -0.0000

Data Index: 1157824 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.4022. Min Act: -0.0001

Data Index: 858997 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.3351. Min Act: -0.0001

Data Index: 441699 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.3783. Min Act: -0.0001

Data Index: 1291423 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2657. Min Act: -0.0000

Data Index: 277425 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2963. Min Act: -0.0000

Data Index: 1233478 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2471. Min Act: -0.0000

Data Index: 987423 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2093. Min Act: -0.0001

Data Index: 1045899 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2495. Min Act: -0.0001

Data Index: 524584 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2509. Min Act: -0.0001

Data Index: 487123 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2797. Min Act: -0.0001

Data Index: 127678 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1061618 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 1.9699. Min Range: -1.9699

Max Act: 1.2163. Min Act: -0.0001

Data Index: 718589 (C4 (Web Text))

Max Activating Token Index: 710