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

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

Neuron 5208 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4099. Min Range: -2.4099

Max Act: 2.4099. Min Act: -0.0000

Data Index: 1242277 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.9991. Min Act: -0.0000

Data Index: 1002271 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.7774. Min Act: -0.0000

Data Index: 577421 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.6993. Min Act: -0.0000

Data Index: 970492 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.6385. Min Act: -0.0000

Data Index: 408148 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5440. Min Act: -0.0000

Data Index: 527051 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.6060. Min Act: -0.0000

Data Index: 877818 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5385. Min Act: -0.0000

Data Index: 783743 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5449. Min Act: -0.0000

Data Index: 413612 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5100. Min Act: 0.0000

Data Index: 1084972 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5126. Min Act: -0.0000

Data Index: 802370 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5969. Min Act: -0.0000

Data Index: 1129945 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.4933. Min Act: -0.0000

Data Index: 1241331 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.4684. Min Act: -0.0000

Data Index: 255153 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1212852 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.4581. Min Act: -0.0000

Data Index: 461649 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5354. Min Act: -0.0000

Data Index: 663257 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5349. Min Act: -0.0000

Data Index: 1358731 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.3537. Min Act: -0.0000

Data Index: 1288547 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 2.4099. Min Range: -2.4099

Max Act: 1.5231. Min Act: 0.0000

Data Index: 1327525 (C4 (Web Text))

Max Activating Token Index: 682