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

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

Neuron 6112 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.5921. Min Act: -0.0000

Data Index: 1647583 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.4244. Min Act: -0.0000

Data Index: 1439495 (Python Code)

Max Activating Token Index: 947

Text #2

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3611. Min Act: -0.0000

Data Index: 1503959 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1523057 (Python Code)

Max Activating Token Index: 187

Text #4

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1529795 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1439934 (Python Code)

Max Activating Token Index: 295

Text #6

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.3059. Min Act: -0.0000

Data Index: 1404500 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1470257 (Python Code)

Max Activating Token Index: 165

Text #8

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1895. Min Act: -0.0000

Data Index: 1547804 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1377580 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1735. Min Act: -0.0000

Data Index: 1638820 (Python Code)

Max Activating Token Index: 185

Text #11

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1364367 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1500298 (Python Code)

Max Activating Token Index: 659

Text #13

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1609248 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1569642 (Python Code)

Max Activating Token Index: 374

Text #15

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.1764. Min Act: -0.0000

Data Index: 1626180 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 1.5921. Min Range: -1.5921

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1418096 (Python Code)

Max Activating Token Index: 936

Text #17

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0314. Min Act: -0.0000

Data Index: 1467628 (Python Code)

Max Activating Token Index: 849

Text #18

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1569860 (Python Code)

Max Activating Token Index: 153

Text #19

Max Range: 1.5921. Min Range: -1.5921

Max Act: 1.0763. Min Act: -0.0000

Data Index: 1408683 (Python Code)

Max Activating Token Index: 436