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

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

Neuron 2664 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.7932. Min Act: -0.0000

Data Index: 800205 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.6643. Min Act: -0.0000

Data Index: 1153217 (C4 (Web Text))

Max Activating Token Index: 470

Text #2

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.5022. Min Act: -0.0000

Data Index: 253060 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.5705. Min Act: -0.0000

Data Index: 326237 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.4371. Min Act: -0.0000

Data Index: 900389 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.4418. Min Act: -0.0000

Data Index: 669955 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1567214 (Python Code)

Max Activating Token Index: 360

Text #7

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1611160 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2558. Min Act: -0.0000

Data Index: 577041 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1462983 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1148607 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2396. Min Act: -0.0000

Data Index: 724464 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.3723. Min Act: -0.0000

Data Index: 491534 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2664. Min Act: -0.0000

Data Index: 858330 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.1376. Min Act: -0.0000

Data Index: 235518 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2504. Min Act: -0.0000

Data Index: 1142277 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2415. Min Act: -0.0000

Data Index: 1522920 (Python Code)

Max Activating Token Index: 301

Text #17

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2223. Min Act: -0.0000

Data Index: 880093 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2193. Min Act: -0.0000

Data Index: 1445214 (Python Code)

Max Activating Token Index: 784

Text #19

Max Range: 1.7932. Min Range: -1.7932

Max Act: 1.2091. Min Act: -0.0000

Data Index: 1254625 (C4 (Web Text))

Max Activating Token Index: 116