Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1274 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9872. Min Act: -0.0001

Data Index: 1475938 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.9561. Min Act: -0.0001

Data Index: 1381948 (Python Code)

Max Activating Token Index: 82

Text #2

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1642121 (Python Code)

Max Activating Token Index: 107

Text #3

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8302. Min Act: -0.0001

Data Index: 1433091 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8526. Min Act: -0.0001

Data Index: 1505429 (Python Code)

Max Activating Token Index: 193

Text #5

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8507. Min Act: -0.0001

Data Index: 1573581 (Python Code)

Max Activating Token Index: 92

Text #6

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8343. Min Act: -0.0001

Data Index: 1537915 (Python Code)

Max Activating Token Index: 373

Text #7

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7873. Min Act: -0.0001

Data Index: 1581319 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8105. Min Act: -0.0001

Data Index: 1430533 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8576. Min Act: -0.0001

Data Index: 1651914 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7563. Min Act: -0.0001

Data Index: 1418149 (Python Code)

Max Activating Token Index: 167

Text #11

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8309. Min Act: -0.0001

Data Index: 1330583 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7735. Min Act: -0.0001

Data Index: 1514449 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1471797 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7925. Min Act: -0.0001

Data Index: 1409242 (Python Code)

Max Activating Token Index: 118

Text #15

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8400. Min Act: -0.0001

Data Index: 1551875 (Python Code)

Max Activating Token Index: 532

Text #16

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.7788. Min Act: -0.0001

Data Index: 1590177 (Python Code)

Max Activating Token Index: 117

Text #17

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8544. Min Act: -0.0001

Data Index: 1628147 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8216. Min Act: -0.0001

Data Index: 1236369 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.9872. Min Range: -0.9872

Max Act: 0.8242. Min Act: -0.0001

Data Index: 1400114 (Python Code)

Max Activating Token Index: 302