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

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

Neuron 5418 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: 0.2572. Min Range: -0.2572

Max Act: 0.2572. Min Act: -0.0000

Data Index: 964702 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2498. Min Act: -0.0000

Data Index: 1076174 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2531. Min Act: -0.0000

Data Index: 988034 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2300. Min Act: -0.0000

Data Index: 991314 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2104. Min Act: -0.0000

Data Index: 367726 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2394. Min Act: -0.0001

Data Index: 250528 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2312. Min Act: -0.0000

Data Index: 507730 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2086. Min Act: -0.0000

Data Index: 688596 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2208. Min Act: -0.0001

Data Index: 421885 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1950. Min Act: -0.0001

Data Index: 839618 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2000. Min Act: -0.0000

Data Index: 869229 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1965. Min Act: -0.0001

Data Index: 318095 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1893. Min Act: -0.0001

Data Index: 42865 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2061. Min Act: -0.0000

Data Index: 710395 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2047. Min Act: -0.0000

Data Index: 288702 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1956. Min Act: -0.0000

Data Index: 824129 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1103202 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2000. Min Act: -0.0001

Data Index: 944395 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.1944. Min Act: -0.0000

Data Index: 229413 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.2572. Min Range: -0.2572

Max Act: 0.2046. Min Act: -0.0000

Data Index: 2792 (C4 (Web Text))

Max Activating Token Index: 670