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

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

Neuron 4380 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.3154. Min Act: -0.0000

Data Index: 1471696 (Python Code)

Max Activating Token Index: 590

Text #1

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.5277. Min Act: -0.0000

Data Index: 1518254 (Python Code)

Max Activating Token Index: 418

Text #2

Max Range: 3.5277. Min Range: -3.5277

Max Act: 3.4728. Min Act: -0.0000

Data Index: 1211283 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.7221. Min Act: -0.0000

Data Index: 392094 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.8193. Min Act: -0.0000

Data Index: 1568601 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.7922. Min Act: -0.0000

Data Index: 1461667 (Python Code)

Max Activating Token Index: 991

Text #6

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.9186. Min Act: -0.0000

Data Index: 304107 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 3.5277. Min Range: -3.5277

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1629143 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.3580. Min Act: -0.0000

Data Index: 1218926 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2214. Min Act: -0.0000

Data Index: 155111 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.3028. Min Act: -0.0000

Data Index: 1609837 (Python Code)

Max Activating Token Index: 865

Text #11

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2854. Min Act: -0.0000

Data Index: 663400 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.1343. Min Act: -0.0000

Data Index: 1606521 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2524. Min Act: -0.0000

Data Index: 359396 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2275. Min Act: -0.0000

Data Index: 1221408 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2289. Min Act: -0.0000

Data Index: 522003 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.2259. Min Act: -0.0000

Data Index: 364135 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1534520 (Python Code)

Max Activating Token Index: 903

Text #18

Max Range: 3.5277. Min Range: -3.5277

Max Act: 1.9881. Min Act: -0.0000

Data Index: 1639971 (Python Code)

Max Activating Token Index: 523

Text #19

Max Range: 3.5277. Min Range: -3.5277

Max Act: 2.1939. Min Act: -0.0000

Data Index: 1343510 (C4 (Web Text))

Max Activating Token Index: 428