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

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

Neuron 1560 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.5866. Min Act: -0.0000

Data Index: 297481 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3493. Min Act: -0.0000

Data Index: 4723 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.4008. Min Act: -0.0000

Data Index: 289943 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.4374. Min Act: -0.0000

Data Index: 99279 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.3761. Min Act: -0.0000

Data Index: 9981 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2289. Min Act: -0.0000

Data Index: 453604 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2292. Min Act: -0.0000

Data Index: 135383 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.2910. Min Act: -0.0000

Data Index: 1121429 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1269970 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1142. Min Act: -0.0000

Data Index: 33390 (C4 (Web Text))

Max Activating Token Index: 161

Text #10

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1758. Min Act: -0.0000

Data Index: 696710 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1332815 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1527. Min Act: -0.0000

Data Index: 617166 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.0777. Min Act: -0.0000

Data Index: 775067 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1434. Min Act: -0.0000

Data Index: 17281 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1081. Min Act: -0.0000

Data Index: 953680 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1340. Min Act: -0.0000

Data Index: 149351 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.0048. Min Act: -0.0000

Data Index: 917652 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1134. Min Act: -0.0000

Data Index: 1237815 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.5866. Min Range: -1.5866

Max Act: 1.1125. Min Act: -0.0000

Data Index: 208987 (C4 (Web Text))

Max Activating Token Index: 811