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

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

Neuron 2550 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6726. Min Act: -0.0000

Data Index: 958721 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1176563 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1032379 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6863. Min Act: -0.0000

Data Index: 244845 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6419. Min Act: -0.0000

Data Index: 948585 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6258. Min Act: -0.0000

Data Index: 1158912 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1339726 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6136. Min Act: -0.0000

Data Index: 702419 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1294699 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6140. Min Act: -0.0000

Data Index: 558042 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6136. Min Act: -0.0000

Data Index: 325433 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1062854 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5929. Min Act: -0.0000

Data Index: 541326 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5948. Min Act: -0.0000

Data Index: 377620 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5554. Min Act: -0.0000

Data Index: 832078 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5901. Min Act: -0.0000

Data Index: 224583 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6248. Min Act: -0.0000

Data Index: 442311 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6050. Min Act: -0.0000

Data Index: 805026 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6018. Min Act: -0.0000

Data Index: 205712 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5834. Min Act: -0.0000

Data Index: 309167 (C4 (Web Text))

Max Activating Token Index: 860