Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1945 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4942. Min Act: -0.0006

Data Index: 1647722 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4670. Min Act: -0.0006

Data Index: 20325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4413. Min Act: -0.0006

Data Index: 1404121 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4387. Min Act: -0.0006

Data Index: 82366 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4240. Min Act: -0.0005

Data Index: 1567872 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4322. Min Act: -0.0005

Data Index: 1368498 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4292. Min Act: -0.0006

Data Index: 1476478 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4157. Min Act: -0.0005

Data Index: 1560076 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4071. Min Act: -0.0005

Data Index: 1380808 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4167. Min Act: -0.0005

Data Index: 1517888 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4129. Min Act: -0.0006

Data Index: 1653666 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3999. Min Act: -0.0006

Data Index: 1406584 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.4215. Min Act: -0.0005

Data Index: 1566922 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3870. Min Act: -0.0005

Data Index: 1404247 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3957. Min Act: -0.0006

Data Index: 913058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3785. Min Act: -0.0006

Data Index: 580283 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3919. Min Act: -0.0005

Data Index: 1630939 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3643. Min Act: -0.0006

Data Index: 453029 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3515. Min Act: -0.0006

Data Index: 61472 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.4942. Min Range: -0.4942

Max Act: 0.3605. Min Act: -0.0006

Data Index: 1547512 (Python Code)

Max Activating Token Index: 1023