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

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

Neuron 3605 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3367. Min Act: -0.0001

Data Index: 520377 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3439. Min Act: -0.0001

Data Index: 1325872 (C4 (Web Text))

Max Activating Token Index: 765

Text #2

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.3077. Min Act: -0.0001

Data Index: 512855 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2558. Min Act: -0.0000

Data Index: 288128 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2419. Min Act: -0.0001

Data Index: 838967 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2090. Min Act: -0.0000

Data Index: 957795 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1181039 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2094. Min Act: -0.0001

Data Index: 747435 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.2120. Min Act: -0.0001

Data Index: 439968 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1938. Min Act: -0.0001

Data Index: 757027 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1887. Min Act: -0.0001

Data Index: 619652 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1771. Min Act: -0.0000

Data Index: 232733 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1887. Min Act: -0.0000

Data Index: 717304 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1800. Min Act: -0.0000

Data Index: 757505 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1794. Min Act: -0.0000

Data Index: 845874 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1843. Min Act: -0.0000

Data Index: 486193 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1716. Min Act: -0.0000

Data Index: 286355 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1876. Min Act: -0.0001

Data Index: 34125 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1324251 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 0.3439. Min Range: -0.3439

Max Act: 0.1869. Min Act: -0.0000

Data Index: 369460 (C4 (Web Text))

Max Activating Token Index: 828