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

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

Neuron 3603 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.2041. Min Act: -0.0001

Data Index: 283893 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.1626. Min Act: -0.0002

Data Index: 4935 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9879. Min Act: -0.0001

Data Index: 957907 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 1.2041. Min Range: -1.2041

Max Act: 1.0344. Min Act: -0.0002

Data Index: 755 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.9766. Min Act: -0.0001

Data Index: 431142 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8381. Min Act: -0.0002

Data Index: 377770 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8479. Min Act: -0.0002

Data Index: 172236 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8249. Min Act: -0.0002

Data Index: 1076711 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.8022. Min Act: -0.0002

Data Index: 1276849 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7176. Min Act: -0.0001

Data Index: 404507 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7882. Min Act: -0.0002

Data Index: 1228859 (C4 (Web Text))

Max Activating Token Index: 5

Text #11

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7814. Min Act: -0.0002

Data Index: 1346313 (C4 (Web Text))

Max Activating Token Index: 72

Text #12

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7807. Min Act: -0.0002

Data Index: 1046238 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7178. Min Act: -0.0002

Data Index: 65161 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7597. Min Act: -0.0001

Data Index: 1309216 (C4 (Web Text))

Max Activating Token Index: 99

Text #15

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7983. Min Act: -0.0002

Data Index: 414800 (C4 (Web Text))

Max Activating Token Index: 905

Text #16

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7129. Min Act: -0.0001

Data Index: 785378 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7718. Min Act: -0.0002

Data Index: 1182503 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7591. Min Act: -0.0002

Data Index: 359161 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 1.2041. Min Range: -1.2041

Max Act: 0.7080. Min Act: -0.0001

Data Index: 335893 (C4 (Web Text))

Max Activating Token Index: 224