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

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

Neuron 1886 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3330. Min Act: -0.0002

Data Index: 359723 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3348. Min Act: -0.0001

Data Index: 585771 (C4 (Web Text))

Max Activating Token Index: 435

Text #2

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1184029 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3253. Min Act: -0.0001

Data Index: 146741 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1516223 (Python Code)

Max Activating Token Index: 971

Text #5

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3287. Min Act: -0.0001

Data Index: 1309712 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3305. Min Act: -0.0001

Data Index: 230595 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3297. Min Act: -0.0001

Data Index: 274290 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3266. Min Act: -0.0001

Data Index: 410117 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1134608 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3070. Min Act: -0.0001

Data Index: 938341 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3135. Min Act: -0.0001

Data Index: 1541766 (Python Code)

Max Activating Token Index: 915

Text #12

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3054. Min Act: -0.0001

Data Index: 1377117 (Python Code)

Max Activating Token Index: 767

Text #13

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3060. Min Act: -0.0001

Data Index: 846708 (C4 (Web Text))

Max Activating Token Index: 744

Text #14

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3029. Min Act: -0.0001

Data Index: 425911 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3101. Min Act: -0.0001

Data Index: 1408982 (Python Code)

Max Activating Token Index: 480

Text #16

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3064. Min Act: -0.0001

Data Index: 157250 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.2999. Min Act: -0.0001

Data Index: 1378079 (Python Code)

Max Activating Token Index: 947

Text #18

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3040. Min Act: -0.0001

Data Index: 1484767 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 0.3383. Min Range: -0.3383

Max Act: 0.3053. Min Act: -0.0001

Data Index: 68356 (C4 (Web Text))

Max Activating Token Index: 608