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

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

Neuron 3270 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4698. Min Range: -4.4698

Max Act: 4.2946. Min Act: -0.0000

Data Index: 1647174 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 4.4698. Min Range: -4.4698

Max Act: 4.4698. Min Act: -0.0000

Data Index: 1639161 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 4.4698. Min Range: -4.4698

Max Act: 4.0242. Min Act: -0.0000

Data Index: 1452745 (Python Code)

Max Activating Token Index: 716

Text #3

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.9594. Min Act: -0.0000

Data Index: 1624862 (Python Code)

Max Activating Token Index: 190

Text #4

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.6465. Min Act: -0.0000

Data Index: 1370076 (Python Code)

Max Activating Token Index: 364

Text #5

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.5446. Min Act: -0.0000

Data Index: 1524585 (Python Code)

Max Activating Token Index: 244

Text #6

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.2851. Min Act: -0.0000

Data Index: 1498615 (Python Code)

Max Activating Token Index: 303

Text #7

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.5445. Min Act: -0.0000

Data Index: 1404889 (Python Code)

Max Activating Token Index: 136

Text #8

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.5144. Min Act: -0.0000

Data Index: 1370986 (Python Code)

Max Activating Token Index: 394

Text #9

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.2117. Min Act: -0.0000

Data Index: 1481369 (Python Code)

Max Activating Token Index: 548

Text #10

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.4091. Min Act: -0.0000

Data Index: 1409145 (Python Code)

Max Activating Token Index: 200

Text #11

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.0474. Min Act: -0.0000

Data Index: 1367239 (Python Code)

Max Activating Token Index: 411

Text #12

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.2126. Min Act: -0.0000

Data Index: 1550937 (Python Code)

Max Activating Token Index: 832

Text #13

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.3155. Min Act: -0.0000

Data Index: 1397854 (Python Code)

Max Activating Token Index: 111

Text #14

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.0094. Min Act: -0.0000

Data Index: 1366616 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.1259. Min Act: -0.0000

Data Index: 1536620 (Python Code)

Max Activating Token Index: 983

Text #16

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.0260. Min Act: -0.0000

Data Index: 1546189 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 4.4698. Min Range: -4.4698

Max Act: 2.9238. Min Act: -0.0000

Data Index: 1588384 (Python Code)

Max Activating Token Index: 400

Text #18

Max Range: 4.4698. Min Range: -4.4698

Max Act: 3.0562. Min Act: -0.0000

Data Index: 1436991 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 4.4698. Min Range: -4.4698

Max Act: 2.7571. Min Act: -0.0000

Data Index: 1580819 (Python Code)

Max Activating Token Index: 163