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

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

Neuron 345 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5757. Min Act: -0.0001

Data Index: 1592401 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1504306 (Python Code)

Max Activating Token Index: 964

Text #2

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4953. Min Act: -0.0001

Data Index: 1463670 (Python Code)

Max Activating Token Index: 285

Text #3

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5788. Min Act: -0.0001

Data Index: 1598264 (Python Code)

Max Activating Token Index: 767

Text #4

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4976. Min Act: -0.0000

Data Index: 364664 (C4 (Web Text))

Max Activating Token Index: 436

Text #5

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4681. Min Act: -0.0001

Data Index: 1517161 (Python Code)

Max Activating Token Index: 448

Text #6

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4661. Min Act: -0.0000

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1482369 (Python Code)

Max Activating Token Index: 926

Text #8

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4373. Min Act: -0.0001

Data Index: 1431419 (Python Code)

Max Activating Token Index: 402

Text #9

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1571803 (Python Code)

Max Activating Token Index: 196

Text #10

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4162. Min Act: -0.0001

Data Index: 921227 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4043. Min Act: -0.0001

Data Index: 1472596 (Python Code)

Max Activating Token Index: 333

Text #12

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4142. Min Act: -0.0000

Data Index: 1422376 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4092. Min Act: -0.0000

Data Index: 1594364 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4044. Min Act: -0.0000

Data Index: 540803 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1445324 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3883. Min Act: -0.0001

Data Index: 1620886 (Python Code)

Max Activating Token Index: 66

Text #17

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3656. Min Act: -0.0000

Data Index: 1468159 (Python Code)

Max Activating Token Index: 531

Text #18

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3480. Min Act: -0.0001

Data Index: 1473659 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.3619. Min Act: -0.0001

Data Index: 81792 (C4 (Web Text))

Max Activating Token Index: 599