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

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

Neuron 3632 in Layer 1

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: 0.2777. Min Range: -0.2777

Max Act: 0.2777. Min Act: -0.0002

Data Index: 1586317 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2722. Min Act: -0.0002

Data Index: 1455944 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2690. Min Act: -0.0002

Data Index: 1381578 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2605. Min Act: -0.0002

Data Index: 638325 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2560. Min Act: -0.0002

Data Index: 1456538 (Python Code)

Max Activating Token Index: 780

Text #5

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2593. Min Act: -0.0002

Data Index: 1481255 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2574. Min Act: -0.0002

Data Index: 1642607 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2607. Min Act: -0.0002

Data Index: 430362 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2497. Min Act: -0.0002

Data Index: 1408755 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2454. Min Act: -0.0002

Data Index: 1453974 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2472. Min Act: -0.0002

Data Index: 1455085 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2483. Min Act: -0.0002

Data Index: 1371738 (Python Code)

Max Activating Token Index: 136

Text #12

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2479. Min Act: -0.0002

Data Index: 1559142 (Python Code)

Max Activating Token Index: 129

Text #13

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2446. Min Act: -0.0002

Data Index: 1590201 (Python Code)

Max Activating Token Index: 43

Text #14

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2496. Min Act: -0.0002

Data Index: 1578799 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2420. Min Act: -0.0002

Data Index: 1612108 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2436. Min Act: -0.0002

Data Index: 1656380 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2395. Min Act: -0.0002

Data Index: 1431150 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2422. Min Act: -0.0002

Data Index: 1607262 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 0.2777. Min Range: -0.2777

Max Act: 0.2409. Min Act: -0.0002

Data Index: 1572820 (Python Code)

Max Activating Token Index: 761