Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3613 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4524. Min Range: -3.4524

Max Act: 3.4524. Min Act: -0.0000

Data Index: 1183074 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 3.4524. Min Range: -3.4524

Max Act: 3.0385. Min Act: -0.0000

Data Index: 571008 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.9498. Min Act: -0.0000

Data Index: 1092786 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 3.4524. Min Range: -3.4524

Max Act: 3.0129. Min Act: -0.0000

Data Index: 1189219 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.7819. Min Act: -0.0000

Data Index: 759897 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.6922. Min Act: -0.0000

Data Index: 503725 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.6595. Min Act: -0.0000

Data Index: 368346 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.9140. Min Act: -0.0000

Data Index: 446830 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.5398. Min Act: -0.0000

Data Index: 758048 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.6372. Min Act: -0.0000

Data Index: 989405 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.4764. Min Act: -0.0000

Data Index: 642512 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.5732. Min Act: -0.0000

Data Index: 1194269 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.5528. Min Act: -0.0000

Data Index: 845485 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.3593. Min Act: -0.0000

Data Index: 134609 (C4 (Web Text))

Max Activating Token Index: 877

Text #14

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.6026. Min Act: -0.0000

Data Index: 178274 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.3448. Min Act: -0.0000

Data Index: 942213 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.4647. Min Act: -0.0000

Data Index: 645490 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.3080. Min Act: -0.0000

Data Index: 679824 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.3040. Min Act: -0.0000

Data Index: 1115440 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 3.4524. Min Range: -3.4524

Max Act: 2.3919. Min Act: -0.0000

Data Index: 786715 (C4 (Web Text))

Max Activating Token Index: 419