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

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

Neuron 2480 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2792. Min Range: -2.2792

Max Act: 2.2792. Min Act: -0.0000

Data Index: 1394743 (Python Code)

Max Activating Token Index: 951

Text #1

Max Range: 2.2792. Min Range: -2.2792

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1641229 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 2.2792. Min Range: -2.2792

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1493565 (Python Code)

Max Activating Token Index: 128

Text #3

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.9954. Min Act: -0.0000

Data Index: 1535557 (Python Code)

Max Activating Token Index: 112

Text #4

Max Range: 2.2792. Min Range: -2.2792

Max Act: 2.0921. Min Act: -0.0000

Data Index: 1563806 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.8554. Min Act: -0.0000

Data Index: 1649953 (Python Code)

Max Activating Token Index: 36

Text #6

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.5934. Min Act: -0.0000

Data Index: 1613209 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.5672. Min Act: -0.0000

Data Index: 1443966 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1495789 (Python Code)

Max Activating Token Index: 313

Text #9

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1441179 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4480. Min Act: -0.0000

Data Index: 1651077 (Python Code)

Max Activating Token Index: 318

Text #11

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1603721 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1479656 (Python Code)

Max Activating Token Index: 694

Text #13

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4398. Min Act: -0.0000

Data Index: 1372228 (Python Code)

Max Activating Token Index: 782

Text #14

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.3491. Min Act: -0.0000

Data Index: 1588446 (Python Code)

Max Activating Token Index: 264

Text #15

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1426508 (Python Code)

Max Activating Token Index: 962

Text #16

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1551100 (Python Code)

Max Activating Token Index: 276

Text #17

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1541618 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1493430 (Python Code)

Max Activating Token Index: 18

Text #19

Max Range: 2.2792. Min Range: -2.2792

Max Act: 1.2094. Min Act: -0.0000

Data Index: 1472815 (Python Code)

Max Activating Token Index: 23