Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3272 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.4069. Min Act: -0.0001

Data Index: 232630 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3846. Min Act: -0.0001

Data Index: 661445 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3713. Min Act: -0.0001

Data Index: 198010 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3327. Min Act: -0.0001

Data Index: 1042527 (C4 (Web Text))

Max Activating Token Index: 641

Text #4

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1049569 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3343. Min Act: -0.0001

Data Index: 947515 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3240. Min Act: -0.0001

Data Index: 443609 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2943. Min Act: -0.0001

Data Index: 951064 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3175. Min Act: -0.0001

Data Index: 635629 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3346. Min Act: -0.0001

Data Index: 541056 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3211. Min Act: -0.0001

Data Index: 272766 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3203. Min Act: -0.0001

Data Index: 1150723 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3013. Min Act: -0.0001

Data Index: 116651 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2988. Min Act: -0.0001

Data Index: 444716 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3111. Min Act: -0.0001

Data Index: 685249 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3094. Min Act: -0.0001

Data Index: 85175 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1513056 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3116. Min Act: -0.0001

Data Index: 653976 (C4 (Web Text))

Max Activating Token Index: 44

Text #18

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.3098. Min Act: -0.0001

Data Index: 1343786 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.4069. Min Range: -0.4069

Max Act: 0.2982. Min Act: -0.0001

Data Index: 1130938 (C4 (Web Text))

Max Activating Token Index: 113