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

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

Neuron 943 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.6999. Min Act: -0.0000

Data Index: 1625584 (Python Code)

Max Activating Token Index: 275

Text #1

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.7778. Min Act: -0.0000

Data Index: 1598510 (Python Code)

Max Activating Token Index: 316

Text #2

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.2333. Min Act: -0.0000

Data Index: 1389646 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8654. Min Act: -0.0000

Data Index: 1443857 (Python Code)

Max Activating Token Index: 269

Text #4

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.7718. Min Act: -0.0000

Data Index: 1542531 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.9424. Min Act: -0.0000

Data Index: 1386400 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.9105. Min Act: -0.0000

Data Index: 1595821 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.7345. Min Act: -0.0000

Data Index: 1470532 (Python Code)

Max Activating Token Index: 115

Text #8

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8990. Min Act: -0.0000

Data Index: 1573265 (Python Code)

Max Activating Token Index: 357

Text #9

Max Range: 6.2333. Min Range: -6.2333

Max Act: 6.0631. Min Act: -0.0000

Data Index: 1558603 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8691. Min Act: -0.0000

Data Index: 1528219 (Python Code)

Max Activating Token Index: 123

Text #11

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.6620. Min Act: -0.0000

Data Index: 1554299 (Python Code)

Max Activating Token Index: 164

Text #12

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.7329. Min Act: -0.0000

Data Index: 1397870 (Python Code)

Max Activating Token Index: 882

Text #13

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.9216. Min Act: -0.0000

Data Index: 1390026 (Python Code)

Max Activating Token Index: 597

Text #14

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8882. Min Act: -0.0000

Data Index: 1428748 (Python Code)

Max Activating Token Index: 198

Text #15

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.7132. Min Act: -0.0000

Data Index: 1498426 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8935. Min Act: -0.0000

Data Index: 1430677 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.6884. Min Act: -0.0000

Data Index: 1415426 (Python Code)

Max Activating Token Index: 159

Text #18

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.5141. Min Act: -0.0000

Data Index: 1461362 (Python Code)

Max Activating Token Index: 261

Text #19

Max Range: 6.2333. Min Range: -6.2333

Max Act: 5.8530. Min Act: -0.0000

Data Index: 1432563 (Python Code)

Max Activating Token Index: 404