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

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

Neuron 2900 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1841. Min Range: -3.1841

Max Act: 3.1841. Min Act: -0.0001

Data Index: 805444 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 3.1841. Min Range: -3.1841

Max Act: 2.6260. Min Act: -0.0001

Data Index: 905648 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 3.1841. Min Range: -3.1841

Max Act: 1.0068. Min Act: -0.0001

Data Index: 508475 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.1841. Min Range: -3.1841

Max Act: 1.1650. Min Act: -0.0001

Data Index: 149511 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 3.1841. Min Range: -3.1841

Max Act: 1.2225. Min Act: -0.0001

Data Index: 1078470 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.8074. Min Act: -0.0001

Data Index: 840939 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.7084. Min Act: -0.0001

Data Index: 174332 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6412. Min Act: -0.0001

Data Index: 18232 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6538. Min Act: -0.0001

Data Index: 706144 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6405. Min Act: -0.0001

Data Index: 322144 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6406. Min Act: -0.0001

Data Index: 1147774 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6520. Min Act: -0.0001

Data Index: 773584 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6303. Min Act: -0.0001

Data Index: 489225 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1263845 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.6293. Min Act: -0.0001

Data Index: 332713 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.5483. Min Act: -0.0001

Data Index: 310027 (C4 (Web Text))

Max Activating Token Index: 643

Text #16

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.5950. Min Act: -0.0001

Data Index: 622384 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.5861. Min Act: -0.0001

Data Index: 807323 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.5620. Min Act: -0.0001

Data Index: 277705 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 3.1841. Min Range: -3.1841

Max Act: 0.5721. Min Act: -0.0001

Data Index: 1293816 (C4 (Web Text))

Max Activating Token Index: 758