Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4372 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4921. Min Act: -0.0000

Data Index: 135619 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4241. Min Act: 0.0000

Data Index: 960128 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1458547 (Python Code)

Max Activating Token Index: 100

Text #3

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.4203. Min Act: -0.0000

Data Index: 1095863 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1562649 (Python Code)

Max Activating Token Index: 196

Text #5

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1580981 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3917. Min Act: -0.0000

Data Index: 390683 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3938. Min Act: -0.0000

Data Index: 992356 (C4 (Web Text))

Max Activating Token Index: 262

Text #8

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3655. Min Act: -0.0000

Data Index: 1128914 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3644. Min Act: -0.0000

Data Index: 806518 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3611. Min Act: -0.0000

Data Index: 36181 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3415. Min Act: -0.0000

Data Index: 647387 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3617. Min Act: -0.0000

Data Index: 1410193 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3399. Min Act: -0.0000

Data Index: 344469 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3273. Min Act: -0.0000

Data Index: 621547 (C4 (Web Text))

Max Activating Token Index: 500

Text #15

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3227. Min Act: -0.0000

Data Index: 771363 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3340. Min Act: -0.0000

Data Index: 710723 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3279. Min Act: -0.0000

Data Index: 1656518 (Python Code)

Max Activating Token Index: 906

Text #18

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1322924 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.4921. Min Range: -0.4921

Max Act: 0.3341. Min Act: -0.0000

Data Index: 1279750 (C4 (Web Text))

Max Activating Token Index: 578