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

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

Neuron 3829 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3510. Min Act: -0.0000

Data Index: 182406 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1146665 (C4 (Web Text))

Max Activating Token Index: 901

Text #2

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3131. Min Act: -0.0000

Data Index: 1054164 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.3082. Min Act: -0.0000

Data Index: 256139 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2937. Min Act: -0.0000

Data Index: 656705 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2866. Min Act: -0.0000

Data Index: 520180 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2860. Min Act: -0.0000

Data Index: 531550 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2738. Min Act: -0.0000

Data Index: 556759 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2580. Min Act: -0.0000

Data Index: 800480 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2734. Min Act: -0.0000

Data Index: 497112 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2494. Min Act: -0.0000

Data Index: 304241 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2653. Min Act: -0.0000

Data Index: 1113590 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1094161 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2526. Min Act: -0.0000

Data Index: 878006 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1358015 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2429. Min Act: -0.0000

Data Index: 635689 (C4 (Web Text))

Max Activating Token Index: 287

Text #16

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2407. Min Act: -0.0000

Data Index: 483155 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2489. Min Act: -0.0000

Data Index: 992557 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2299. Min Act: -0.0000

Data Index: 178089 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.3510. Min Range: -0.3510

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1191523 (C4 (Web Text))

Max Activating Token Index: 775