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

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

Neuron 2961 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.3189. Min Act: -0.0000

Data Index: 738271 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2647. Min Act: -0.0001

Data Index: 30246 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2686. Min Act: -0.0001

Data Index: 1134729 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2696. Min Act: -0.0000

Data Index: 138379 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2640. Min Act: -0.0001

Data Index: 626665 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2418. Min Act: -0.0000

Data Index: 481099 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2531. Min Act: -0.0000

Data Index: 934765 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2416. Min Act: -0.0000

Data Index: 985505 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2325. Min Act: -0.0001

Data Index: 289369 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2287. Min Act: -0.0001

Data Index: 480723 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2210. Min Act: -0.0001

Data Index: 831402 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2203. Min Act: -0.0001

Data Index: 403980 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2136. Min Act: -0.0001

Data Index: 1089782 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2134. Min Act: -0.0001

Data Index: 700988 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1261832 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2100. Min Act: -0.0001

Data Index: 86186 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2082. Min Act: -0.0000

Data Index: 828885 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1937. Min Act: -0.0000

Data Index: 897156 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.2055. Min Act: -0.0001

Data Index: 1304040 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.3189. Min Range: -0.3189

Max Act: 0.1942. Min Act: -0.0000

Data Index: 639315 (C4 (Web Text))

Max Activating Token Index: 244