Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1842 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1543328 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1379839 (Python Code)

Max Activating Token Index: 228

Text #2

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2649. Min Act: -0.0001

Data Index: 1404768 (Python Code)

Max Activating Token Index: 209

Text #3

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1401323 (Python Code)

Max Activating Token Index: 983

Text #4

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1542745 (Python Code)

Max Activating Token Index: 740

Text #5

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2614. Min Act: -0.0001

Data Index: 1563056 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2464. Min Act: -0.0001

Data Index: 1548080 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1655911 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1450738 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1489843 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2538. Min Act: -0.0001

Data Index: 1478795 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1520090 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2288. Min Act: -0.0001

Data Index: 1458419 (Python Code)

Max Activating Token Index: 516

Text #13

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1570549 (Python Code)

Max Activating Token Index: 611

Text #14

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1631337 (Python Code)

Max Activating Token Index: 415

Text #15

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2381. Min Act: -0.0001

Data Index: 1472809 (Python Code)

Max Activating Token Index: 652

Text #16

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2397. Min Act: -0.0001

Data Index: 1587197 (Python Code)

Max Activating Token Index: 192

Text #17

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2240. Min Act: -0.0001

Data Index: 1575747 (Python Code)

Max Activating Token Index: 351

Text #18

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2389. Min Act: -0.0001

Data Index: 1483644 (Python Code)

Max Activating Token Index: 798

Text #19

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2213. Min Act: -0.0001

Data Index: 1539323 (Python Code)

Max Activating Token Index: 630