Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 153 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.6059. Min Act: -0.0001

Data Index: 392307 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.5422. Min Act: -0.0001

Data Index: 967065 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.4600. Min Act: -0.0001

Data Index: 1253074 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3799. Min Act: -0.0001

Data Index: 49277 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3983. Min Act: -0.0001

Data Index: 898354 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3469. Min Act: -0.0001

Data Index: 1085086 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3433. Min Act: -0.0001

Data Index: 311567 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3261. Min Act: -0.0001

Data Index: 1107792 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3086. Min Act: -0.0001

Data Index: 451357 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3729. Min Act: -0.0001

Data Index: 247754 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3417. Min Act: -0.0001

Data Index: 1115167 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3805. Min Act: -0.0001

Data Index: 876267 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2576. Min Act: -0.0001

Data Index: 127397 (C4 (Web Text))

Max Activating Token Index: 248

Text #13

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2863. Min Act: -0.0001

Data Index: 1332103 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2813. Min Act: -0.0001

Data Index: 8708 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3088. Min Act: -0.0001

Data Index: 672340 (C4 (Web Text))

Max Activating Token Index: 102

Text #16

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2567. Min Act: -0.0001

Data Index: 915968 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.3047. Min Act: -0.0001

Data Index: 836481 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2991. Min Act: -0.0001

Data Index: 59135 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.6059. Min Range: -1.6059

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1239494 (C4 (Web Text))

Max Activating Token Index: 338