Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3599 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1090. Min Act: -0.0001

Data Index: 366049 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1409197 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1543411 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1543364 (Python Code)

Max Activating Token Index: 35

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0992. Min Act: -0.0001

Data Index: 398639 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1595908 (Python Code)

Max Activating Token Index: 487

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1602842 (Python Code)

Max Activating Token Index: 30

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1417569 (Python Code)

Max Activating Token Index: 355

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1431510 (Python Code)

Max Activating Token Index: 591

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1330550 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1467538 (Python Code)

Max Activating Token Index: 931

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0822. Min Act: -0.0001

Data Index: 228385 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1453690 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1568185 (Python Code)

Max Activating Token Index: 61

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0813. Min Act: -0.0001

Data Index: 760449 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1408523 (Python Code)

Max Activating Token Index: 653

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1373074 (Python Code)

Max Activating Token Index: 239

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1528131 (Python Code)

Max Activating Token Index: 322

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0664. Min Act: -0.0001

Data Index: 1436685 (Python Code)

Max Activating Token Index: 579

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0742. Min Act: -0.0001

Data Index: 202475 (C4 (Web Text))

Max Activating Token Index: 560