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

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

Neuron 5746 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8177. Min Act: -0.0002

Data Index: 1612959 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8197. Min Act: -0.0002

Data Index: 1475591 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8199. Min Act: -0.0002

Data Index: 1455647 (Python Code)

Max Activating Token Index: 160

Text #3

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8240. Min Act: -0.0002

Data Index: 1491092 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8199. Min Act: -0.0002

Data Index: 1390217 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.8180. Min Act: -0.0002

Data Index: 1473230 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7927. Min Act: -0.0002

Data Index: 1563663 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7761. Min Act: -0.0002

Data Index: 1516549 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7683. Min Act: -0.0002

Data Index: 1373230 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7851. Min Act: -0.0002

Data Index: 1580487 (Python Code)

Max Activating Token Index: 427

Text #10

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7620. Min Act: -0.0002

Data Index: 1522881 (Python Code)

Max Activating Token Index: 41

Text #11

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7612. Min Act: -0.0002

Data Index: 1566848 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7520. Min Act: -0.0002

Data Index: 1456990 (Python Code)

Max Activating Token Index: 62

Text #13

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7277. Min Act: -0.0002

Data Index: 1363085 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7398. Min Act: -0.0002

Data Index: 1414182 (Python Code)

Max Activating Token Index: 265

Text #15

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7196. Min Act: -0.0002

Data Index: 1459327 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7317. Min Act: -0.0002

Data Index: 1522867 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7245. Min Act: -0.0002

Data Index: 1655780 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7183. Min Act: -0.0002

Data Index: 1479616 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.8240. Min Range: -0.8240

Max Act: 0.7153. Min Act: -0.0002

Data Index: 1602876 (Python Code)

Max Activating Token Index: 266