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

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

Neuron 2062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7174. Min Range: -4.7174

Max Act: 4.7174. Min Act: -0.0000

Data Index: 1628238 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 4.7174. Min Range: -4.7174

Max Act: 4.3450. Min Act: -0.0000

Data Index: 1425971 (Python Code)

Max Activating Token Index: 367

Text #2

Max Range: 4.7174. Min Range: -4.7174

Max Act: 4.1983. Min Act: -0.0000

Data Index: 1057425 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.9386. Min Act: -0.0000

Data Index: 1513346 (Python Code)

Max Activating Token Index: 302

Text #4

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.6699. Min Act: -0.0000

Data Index: 388798 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.8422. Min Act: -0.0000

Data Index: 357818 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.5590. Min Act: -0.0000

Data Index: 312664 (C4 (Web Text))

Max Activating Token Index: 441

Text #7

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.7055. Min Act: -0.0000

Data Index: 1107146 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.8857. Min Act: -0.0000

Data Index: 1349223 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.4687. Min Act: -0.0000

Data Index: 1414791 (Python Code)

Max Activating Token Index: 23

Text #10

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.4759. Min Act: -0.0000

Data Index: 1595763 (Python Code)

Max Activating Token Index: 291

Text #11

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.7650. Min Act: -0.0000

Data Index: 1462459 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.5734. Min Act: -0.0000

Data Index: 1147640 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.3986. Min Act: -0.0000

Data Index: 1592225 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.3837. Min Act: -0.0000

Data Index: 1419933 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.4947. Min Act: -0.0000

Data Index: 1537154 (Python Code)

Max Activating Token Index: 34

Text #16

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.3085. Min Act: -0.0000

Data Index: 49311 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.2903. Min Act: -0.0000

Data Index: 363042 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.3005. Min Act: -0.0000

Data Index: 1433354 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 4.7174. Min Range: -4.7174

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1486349 (Python Code)

Max Activating Token Index: 833