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

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

Neuron 3483 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: 0.4818. Min Range: -0.4818

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1462777 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1557369 (Python Code)

Max Activating Token Index: 1021

Text #2

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4818. Min Act: -0.0001

Data Index: 614226 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4199. Min Act: -0.0000

Data Index: 1604820 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4277. Min Act: -0.0000

Data Index: 1557978 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3958. Min Act: -0.0000

Data Index: 1553083 (Python Code)

Max Activating Token Index: 35

Text #6

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1463820 (Python Code)

Max Activating Token Index: 646

Text #7

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4039. Min Act: -0.0000

Data Index: 1403728 (Python Code)

Max Activating Token Index: 405

Text #8

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1539395 (Python Code)

Max Activating Token Index: 270

Text #9

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1528716 (Python Code)

Max Activating Token Index: 225

Text #10

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4005. Min Act: -0.0001

Data Index: 1638199 (Python Code)

Max Activating Token Index: 103

Text #11

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3841. Min Act: -0.0001

Data Index: 1549198 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1523112 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3759. Min Act: -0.0001

Data Index: 1591919 (Python Code)

Max Activating Token Index: 114

Text #14

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3450. Min Act: -0.0000

Data Index: 1515391 (Python Code)

Max Activating Token Index: 261

Text #15

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.4019. Min Act: -0.0001

Data Index: 1483449 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3288. Min Act: -0.0000

Data Index: 1370756 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1480696 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3699. Min Act: -0.0000

Data Index: 1378565 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.4818. Min Range: -0.4818

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1531942 (Python Code)

Max Activating Token Index: 181