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

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

Neuron 5203 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1519119 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1538124 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1574517 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1611656 (Python Code)

Max Activating Token Index: 325

Text #4

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.0100. Min Act: -0.0000

Data Index: 1575004 (Python Code)

Max Activating Token Index: 250

Text #5

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1650268 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1634531 (Python Code)

Max Activating Token Index: 150

Text #7

Max Range: 1.3399. Min Range: -1.3399

Max Act: 1.0476. Min Act: -0.0000

Data Index: 1645099 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8352. Min Act: -0.0000

Data Index: 1405071 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8536. Min Act: -0.0000

Data Index: 1617934 (Python Code)

Max Activating Token Index: 947

Text #10

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1544599 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1617547 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1596960 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8177. Min Act: -0.0000

Data Index: 1616073 (Python Code)

Max Activating Token Index: 688

Text #14

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1637681 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1551064 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1373217 (Python Code)

Max Activating Token Index: 144

Text #17

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8136. Min Act: -0.0000

Data Index: 1654211 (Python Code)

Max Activating Token Index: 153

Text #18

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1622274 (Python Code)

Max Activating Token Index: 89

Text #19

Max Range: 1.3399. Min Range: -1.3399

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1624580 (Python Code)

Max Activating Token Index: 57