Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2368 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0487. Min Range: -1.0487

Max Act: 1.0487. Min Act: -0.0001

Data Index: 1514736 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.9624. Min Act: -0.0001

Data Index: 1521385 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.9482. Min Act: -0.0001

Data Index: 1457601 (Python Code)

Max Activating Token Index: 284

Text #3

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.9528. Min Act: -0.0001

Data Index: 1604533 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.9206. Min Act: -0.0001

Data Index: 1583814 (Python Code)

Max Activating Token Index: 155

Text #5

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1386589 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8887. Min Act: -0.0001

Data Index: 1383310 (Python Code)

Max Activating Token Index: 352

Text #7

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1398224 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8515. Min Act: -0.0001

Data Index: 1504028 (Python Code)

Max Activating Token Index: 603

Text #9

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8677. Min Act: -0.0001

Data Index: 1648036 (Python Code)

Max Activating Token Index: 172

Text #10

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8569. Min Act: -0.0001

Data Index: 1533234 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8220. Min Act: -0.0001

Data Index: 1606718 (Python Code)

Max Activating Token Index: 763

Text #12

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8742. Min Act: -0.0001

Data Index: 1580205 (Python Code)

Max Activating Token Index: 160

Text #13

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1551222 (Python Code)

Max Activating Token Index: 479

Text #14

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8095. Min Act: -0.0001

Data Index: 1475895 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1528445 (Python Code)

Max Activating Token Index: 860

Text #16

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8058. Min Act: -0.0001

Data Index: 1384693 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8282. Min Act: -0.0001

Data Index: 1536773 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.8171. Min Act: -0.0001

Data Index: 1543166 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 1.0487. Min Range: -1.0487

Max Act: 0.7970. Min Act: -0.0001

Data Index: 1637811 (Python Code)

Max Activating Token Index: 179