Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1436 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0994. Min Range: -1.0994

Max Act: 1.0994. Min Act: -0.0001

Data Index: 1361450 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 1.0994. Min Range: -1.0994

Max Act: 1.0124. Min Act: -0.0001

Data Index: 1387006 (Python Code)

Max Activating Token Index: 415

Text #2

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8692. Min Act: -0.0001

Data Index: 619037 (C4 (Web Text))

Max Activating Token Index: 1014

Text #3

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.9586. Min Act: -0.0001

Data Index: 1370478 (Python Code)

Max Activating Token Index: 63

Text #4

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.9793. Min Act: -0.0001

Data Index: 1618164 (Python Code)

Max Activating Token Index: 853

Text #5

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1006854 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8324. Min Act: -0.0001

Data Index: 1517561 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8910. Min Act: -0.0001

Data Index: 1380160 (Python Code)

Max Activating Token Index: 491

Text #8

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8883. Min Act: -0.0001

Data Index: 1507194 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.9070. Min Act: -0.0001

Data Index: 1515028 (Python Code)

Max Activating Token Index: 855

Text #10

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8659. Min Act: -0.0001

Data Index: 1487634 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8535. Min Act: -0.0001

Data Index: 661376 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8037. Min Act: -0.0001

Data Index: 1448827 (Python Code)

Max Activating Token Index: 114

Text #13

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8422. Min Act: -0.0001

Data Index: 1454797 (Python Code)

Max Activating Token Index: 372

Text #14

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.7977. Min Act: -0.0001

Data Index: 1603510 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8094. Min Act: -0.0001

Data Index: 599955 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.8203. Min Act: -0.0001

Data Index: 141067 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.7534. Min Act: -0.0001

Data Index: 1071455 (C4 (Web Text))

Max Activating Token Index: 650

Text #18

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.6746. Min Act: -0.0001

Data Index: 447899 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.0994. Min Range: -1.0994

Max Act: 0.7699. Min Act: -0.0001

Data Index: 841886 (C4 (Web Text))

Max Activating Token Index: 89