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

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

Neuron 3993 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.3211. Min Act: -0.0001

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2716. Min Act: -0.0001

Data Index: 459887 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1306597 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2261. Min Act: -0.0001

Data Index: 697153 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2480. Min Act: -0.0001

Data Index: 1223254 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2442. Min Act: -0.0001

Data Index: 527937 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2307. Min Act: -0.0001

Data Index: 477235 (C4 (Web Text))

Max Activating Token Index: 967

Text #7

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2409. Min Act: -0.0001

Data Index: 37016 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2338. Min Act: -0.0001

Data Index: 1282869 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2411. Min Act: -0.0001

Data Index: 312689 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2411. Min Act: -0.0001

Data Index: 1353444 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2059. Min Act: -0.0001

Data Index: 595384 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2269. Min Act: -0.0001

Data Index: 1060612 (C4 (Web Text))

Max Activating Token Index: 618

Text #13

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2264. Min Act: -0.0001

Data Index: 1175955 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2183. Min Act: -0.0001

Data Index: 591187 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1147065 (C4 (Web Text))

Max Activating Token Index: 475

Text #16

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2384. Min Act: -0.0001

Data Index: 670050 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2117. Min Act: -0.0001

Data Index: 187129 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2219. Min Act: -0.0001

Data Index: 825803 (C4 (Web Text))

Max Activating Token Index: 382

Text #19

Max Range: 0.3211. Min Range: -0.3211

Max Act: 0.2282. Min Act: -0.0001

Data Index: 779882 (C4 (Web Text))

Max Activating Token Index: 446