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

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

Neuron 5154 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.5702. Min Act: -0.0000

Data Index: 325970 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1266822 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.5331. Min Act: -0.0000

Data Index: 546348 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4846. Min Act: 0.0001

Data Index: 211644 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4693. Min Act: -0.0000

Data Index: 874099 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4511. Min Act: -0.0000

Data Index: 1059100 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.3992. Min Act: -0.0000

Data Index: 873970 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4294. Min Act: -0.0000

Data Index: 906808 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4536. Min Act: -0.0000

Data Index: 1223883 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4291. Min Act: -0.0000

Data Index: 987579 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1236431 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1293274 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4081. Min Act: -0.0000

Data Index: 789144 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4086. Min Act: -0.0000

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4217. Min Act: 0.0000

Data Index: 1136396 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.3897. Min Act: -0.0000

Data Index: 700997 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4003. Min Act: -0.0000

Data Index: 943648 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.3976. Min Act: -0.0000

Data Index: 243713 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.5801. Min Range: -0.5801

Max Act: 0.4101. Min Act: -0.0000

Data Index: 362110 (C4 (Web Text))

Max Activating Token Index: 510