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

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

Neuron 990 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: 0.0332. Min Range: -0.0332

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1556935 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0001

Data Index: 1555747 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1461780 (Python Code)

Max Activating Token Index: 9

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1543179 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1613532 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1444884 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1502672 (Python Code)

Max Activating Token Index: 16

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1641277 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1395407 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1456835 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1642043 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1512703 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1409508 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1576384 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1552094 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1559339 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1368626 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1546589 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1505402 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1377956 (Python Code)

Max Activating Token Index: 1