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

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

Neuron 1928 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5747. Min Range: -3.5747

Max Act: 3.5747. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.9020. Min Act: -0.0000

Data Index: 761849 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.7690. Min Act: -0.0000

Data Index: 947883 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.7517. Min Act: -0.0000

Data Index: 1141558 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.7527. Min Act: -0.0000

Data Index: 998410 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.4808. Min Act: -0.0000

Data Index: 378532 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.6288. Min Act: -0.0000

Data Index: 28678 (C4 (Web Text))

Max Activating Token Index: 404

Text #7

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3050. Min Act: -0.0000

Data Index: 452082 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3898. Min Act: -0.0000

Data Index: 474292 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3586. Min Act: -0.0000

Data Index: 322234 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1463193 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3324. Min Act: -0.0000

Data Index: 69077 (C4 (Web Text))

Max Activating Token Index: 126

Text #12

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.3376. Min Act: -0.0000

Data Index: 1045487 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.0502. Min Act: -0.0000

Data Index: 911455 (C4 (Web Text))

Max Activating Token Index: 840

Text #14

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.2828. Min Act: -0.0000

Data Index: 899068 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.2175. Min Act: -0.0000

Data Index: 603391 (C4 (Web Text))

Max Activating Token Index: 128

Text #16

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.0608. Min Act: -0.0000

Data Index: 752819 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.1848. Min Act: -0.0000

Data Index: 1359445 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 3.5747. Min Range: -3.5747

Max Act: 2.1622. Min Act: -0.0000

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 3.5747. Min Range: -3.5747

Max Act: 1.9188. Min Act: -0.0000

Data Index: 1633613 (Python Code)

Max Activating Token Index: 175