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

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

Neuron 3176 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: 0.3780. Min Range: -0.3780

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1571797 (Python Code)

Max Activating Token Index: 699

Text #1

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3780. Min Act: -0.0001

Data Index: 367940 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3491. Min Act: -0.0001

Data Index: 73051 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3405. Min Act: -0.0001

Data Index: 146724 (C4 (Web Text))

Max Activating Token Index: 1022

Text #4

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3286. Min Act: -0.0001

Data Index: 278601 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1395454 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3138. Min Act: -0.0001

Data Index: 302300 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2696. Min Act: -0.0001

Data Index: 1545283 (Python Code)

Max Activating Token Index: 273

Text #8

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1602946 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2980. Min Act: -0.0001

Data Index: 363329 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1149814 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3187. Min Act: -0.0001

Data Index: 893000 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3473. Min Act: -0.0001

Data Index: 962130 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2990. Min Act: -0.0001

Data Index: 1262668 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3122. Min Act: -0.0001

Data Index: 159595 (C4 (Web Text))

Max Activating Token Index: 983

Text #15

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.3126. Min Act: -0.0000

Data Index: 966558 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2761. Min Act: -0.0001

Data Index: 490565 (C4 (Web Text))

Max Activating Token Index: 105

Text #17

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2909. Min Act: -0.0001

Data Index: 832023 (C4 (Web Text))

Max Activating Token Index: 770

Text #18

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2900. Min Act: -0.0001

Data Index: 1262414 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 0.3780. Min Range: -0.3780

Max Act: 0.2534. Min Act: -0.0000

Data Index: 483883 (C4 (Web Text))

Max Activating Token Index: 877