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

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

Neuron 5476 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0994. Min Range: -4.0994

Max Act: 4.0994. Min Act: -0.0000

Data Index: 633192 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.2423. Min Act: -0.0000

Data Index: 434952 (C4 (Web Text))

Max Activating Token Index: 212

Text #2

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.1492. Min Act: -0.0000

Data Index: 33136 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.0280. Min Act: -0.0000

Data Index: 176593 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 4.0994. Min Range: -4.0994

Max Act: 3.0230. Min Act: -0.0000

Data Index: 1102715 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.7551. Min Act: -0.0000

Data Index: 1081286 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.8977. Min Act: -0.0000

Data Index: 242443 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.8475. Min Act: -0.0000

Data Index: 222841 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.5862. Min Act: -0.0000

Data Index: 1346350 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.8478. Min Act: -0.0000

Data Index: 399965 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.4973. Min Act: -0.0000

Data Index: 20505 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.6051. Min Act: -0.0000

Data Index: 680256 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.6025. Min Act: -0.0000

Data Index: 584339 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.7136. Min Act: -0.0000

Data Index: 175953 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.6805. Min Act: -0.0000

Data Index: 261396 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.5392. Min Act: -0.0000

Data Index: 550655 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.6273. Min Act: -0.0000

Data Index: 720837 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.4819. Min Act: -0.0000

Data Index: 1032766 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.4767. Min Act: -0.0000

Data Index: 121127 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 4.0994. Min Range: -4.0994

Max Act: 2.4316. Min Act: -0.0000

Data Index: 892111 (C4 (Web Text))

Max Activating Token Index: 467