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

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

Neuron 1131 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.5847. Min Act: -0.0000

Data Index: 1110383 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.4005. Min Act: -0.0000

Data Index: 1100906 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.2088. Min Act: -0.0000

Data Index: 743067 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.1000. Min Act: -0.0000

Data Index: 702818 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0845. Min Act: -0.0000

Data Index: 1584194 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 2.5847. Min Range: -2.5847

Max Act: 2.0456. Min Act: -0.0000

Data Index: 1142023 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8138. Min Act: -0.0000

Data Index: 50694 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1518242 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.7652. Min Act: -0.0000

Data Index: 1479271 (Python Code)

Max Activating Token Index: 198

Text #9

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.7471. Min Act: -0.0000

Data Index: 792853 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.7056. Min Act: -0.0000

Data Index: 1019041 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.6512. Min Act: -0.0000

Data Index: 1237446 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.6126. Min Act: -0.0000

Data Index: 779690 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.4735. Min Act: -0.0000

Data Index: 1541315 (Python Code)

Max Activating Token Index: 307

Text #14

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.6431. Min Act: -0.0000

Data Index: 589707 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.6433. Min Act: -0.0000

Data Index: 639837 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1651308 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.5850. Min Act: -0.0000

Data Index: 1440187 (Python Code)

Max Activating Token Index: 495

Text #18

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.5495. Min Act: -0.0000

Data Index: 1431279 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 2.5847. Min Range: -2.5847

Max Act: 1.8217. Min Act: -0.0000

Data Index: 422702 (C4 (Web Text))

Max Activating Token Index: 728