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

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

Neuron 2395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1469050 (Python Code)

Max Activating Token Index: 355

Text #1

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.7113. Min Act: -0.0001

Data Index: 1623744 (Python Code)

Max Activating Token Index: 162

Text #2

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6082. Min Act: -0.0001

Data Index: 1424371 (Python Code)

Max Activating Token Index: 628

Text #3

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6147. Min Act: -0.0001

Data Index: 1461538 (Python Code)

Max Activating Token Index: 352

Text #4

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5960. Min Act: -0.0001

Data Index: 1415958 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.6294. Min Act: -0.0001

Data Index: 1364291 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5824. Min Act: -0.0001

Data Index: 1534201 (Python Code)

Max Activating Token Index: 757

Text #7

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1606348 (Python Code)

Max Activating Token Index: 602

Text #8

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5704. Min Act: -0.0001

Data Index: 1591551 (Python Code)

Max Activating Token Index: 309

Text #9

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5656. Min Act: -0.0001

Data Index: 1388459 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5539. Min Act: -0.0001

Data Index: 1639442 (Python Code)

Max Activating Token Index: 943

Text #11

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5410. Min Act: -0.0001

Data Index: 1437818 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1492855 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5275. Min Act: -0.0000

Data Index: 1603508 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1545105 (Python Code)

Max Activating Token Index: 989

Text #15

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1498518 (Python Code)

Max Activating Token Index: 599

Text #16

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5302. Min Act: -0.0001

Data Index: 1387294 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.4965. Min Act: -0.0001

Data Index: 1636818 (Python Code)

Max Activating Token Index: 928

Text #18

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1568758 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 0.7113. Min Range: -0.7113

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1650503 (Python Code)

Max Activating Token Index: 302