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

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

Neuron 2363 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: 0.3181. Min Range: -0.3181

Max Act: 0.3181. Min Act: -0.0001

Data Index: 839452 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2969. Min Act: -0.0001

Data Index: 1168507 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.3011. Min Act: -0.0001

Data Index: 734905 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2677. Min Act: -0.0001

Data Index: 571783 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2645. Min Act: -0.0001

Data Index: 1093782 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2655. Min Act: -0.0001

Data Index: 1355744 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1040781 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2449. Min Act: -0.0001

Data Index: 87760 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2669. Min Act: -0.0001

Data Index: 920146 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2325. Min Act: -0.0001

Data Index: 422751 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2428. Min Act: -0.0001

Data Index: 186809 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2237. Min Act: -0.0001

Data Index: 457968 (C4 (Web Text))

Max Activating Token Index: 745

Text #12

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2472. Min Act: -0.0001

Data Index: 536255 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2403. Min Act: -0.0001

Data Index: 1248688 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2384. Min Act: -0.0001

Data Index: 1357979 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2532. Min Act: -0.0001

Data Index: 1338945 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2157. Min Act: -0.0001

Data Index: 1082715 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2230. Min Act: -0.0001

Data Index: 571417 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2270. Min Act: -0.0001

Data Index: 673694 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.3181. Min Range: -0.3181

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1131302 (C4 (Web Text))

Max Activating Token Index: 527