Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 250 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5797. Min Act: -0.0003

Data Index: 1419662 (Python Code)

Max Activating Token Index: 398

Text #1

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5405. Min Act: -0.0003

Data Index: 1391606 (Python Code)

Max Activating Token Index: 195

Text #2

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5551. Min Act: -0.0003

Data Index: 1631140 (Python Code)

Max Activating Token Index: 111

Text #3

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5942. Min Act: -0.0003

Data Index: 1368396 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5857. Min Act: -0.0003

Data Index: 1647027 (Python Code)

Max Activating Token Index: 645

Text #5

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.5089. Min Act: -0.0003

Data Index: 1499080 (Python Code)

Max Activating Token Index: 62

Text #6

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4868. Min Act: -0.0003

Data Index: 1614915 (Python Code)

Max Activating Token Index: 647

Text #7

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4811. Min Act: -0.0003

Data Index: 1506626 (Python Code)

Max Activating Token Index: 970

Text #8

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4485. Min Act: -0.0003

Data Index: 1573325 (Python Code)

Max Activating Token Index: 281

Text #9

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4803. Min Act: -0.0003

Data Index: 1565049 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4909. Min Act: -0.0003

Data Index: 1449688 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4391. Min Act: -0.0003

Data Index: 1600565 (Python Code)

Max Activating Token Index: 918

Text #12

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4518. Min Act: -0.0003

Data Index: 1406216 (Python Code)

Max Activating Token Index: 461

Text #13

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4319. Min Act: -0.0003

Data Index: 1464143 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4240. Min Act: -0.0003

Data Index: 1422842 (Python Code)

Max Activating Token Index: 180

Text #15

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4150. Min Act: -0.0003

Data Index: 1430414 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4282. Min Act: -0.0003

Data Index: 1618269 (Python Code)

Max Activating Token Index: 207

Text #17

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.3842. Min Act: -0.0003

Data Index: 1532070 (Python Code)

Max Activating Token Index: 245

Text #18

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4114. Min Act: -0.0003

Data Index: 1419370 (Python Code)

Max Activating Token Index: 957

Text #19

Max Range: 0.5942. Min Range: -0.5942

Max Act: 0.4078. Min Act: -0.0003

Data Index: 1607990 (Python Code)

Max Activating Token Index: 396