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

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

Neuron 4435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.8174. Min Act: -0.0000

Data Index: 1445608 (Python Code)

Max Activating Token Index: 402

Text #1

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.2054. Min Act: -0.0000

Data Index: 1504601 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0593. Min Act: -0.0001

Data Index: 1505925 (Python Code)

Max Activating Token Index: 219

Text #3

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0294. Min Act: -0.0000

Data Index: 1500212 (Python Code)

Max Activating Token Index: 248

Text #4

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0558. Min Act: -0.0000

Data Index: 1414020 (Python Code)

Max Activating Token Index: 188

Text #5

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.1571. Min Act: -0.0000

Data Index: 1400969 (Python Code)

Max Activating Token Index: 974

Text #6

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.1290. Min Act: -0.0000

Data Index: 1601304 (Python Code)

Max Activating Token Index: 440

Text #7

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.9931. Min Act: -0.0000

Data Index: 1585434 (Python Code)

Max Activating Token Index: 778

Text #8

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0475. Min Act: -0.0000

Data Index: 1254172 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.9665. Min Act: -0.0001

Data Index: 1386472 (Python Code)

Max Activating Token Index: 211

Text #10

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0084. Min Act: -0.0000

Data Index: 1637507 (Python Code)

Max Activating Token Index: 214

Text #11

Max Range: 2.8174. Min Range: -2.8174

Max Act: 2.0479. Min Act: -0.0000

Data Index: 1518070 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.8319. Min Act: -0.0000

Data Index: 1606989 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.9858. Min Act: -0.0000

Data Index: 1462106 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.9912. Min Act: -0.0000

Data Index: 1415133 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.7915. Min Act: -0.0001

Data Index: 1524067 (Python Code)

Max Activating Token Index: 662

Text #16

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.9115. Min Act: -0.0000

Data Index: 1655340 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.7339. Min Act: -0.0000

Data Index: 827780 (C4 (Web Text))

Max Activating Token Index: 747

Text #18

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.8393. Min Act: -0.0001

Data Index: 1637533 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 2.8174. Min Range: -2.8174

Max Act: 1.8173. Min Act: -0.0000

Data Index: 1600445 (Python Code)

Max Activating Token Index: 82