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

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

Neuron 54 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3697. Min Act: -0.0000

Data Index: 550353 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3186. Min Act: -0.0000

Data Index: 556958 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3403. Min Act: -0.0000

Data Index: 181114 (C4 (Web Text))

Max Activating Token Index: 70

Text #3

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3324. Min Act: -0.0000

Data Index: 764429 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3204. Min Act: -0.0000

Data Index: 91680 (C4 (Web Text))

Max Activating Token Index: 703

Text #5

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3252. Min Act: -0.0000

Data Index: 989151 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3247. Min Act: -0.0000

Data Index: 854552 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3160. Min Act: -0.0000

Data Index: 1147824 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2881. Min Act: -0.0000

Data Index: 81374 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3141. Min Act: -0.0000

Data Index: 601011 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3123. Min Act: -0.0000

Data Index: 1321886 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2996. Min Act: -0.0000

Data Index: 423848 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3135. Min Act: -0.0000

Data Index: 378687 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3216. Min Act: -0.0000

Data Index: 794183 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2997. Min Act: -0.0000

Data Index: 665757 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3121. Min Act: -0.0000

Data Index: 18539 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1110050 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3096. Min Act: -0.0000

Data Index: 68198 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.3055. Min Act: -0.0000

Data Index: 1080987 (C4 (Web Text))

Max Activating Token Index: 157

Text #19

Max Range: 0.3697. Min Range: -0.3697

Max Act: 0.2937. Min Act: -0.0000

Data Index: 136675 (C4 (Web Text))

Max Activating Token Index: 584