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

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

Neuron 2230 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: 1.3943. Min Range: -1.3943

Max Act: 1.3943. Min Act: -0.0000

Data Index: 1036055 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1086721 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0088. Min Act: -0.0000

Data Index: 314863 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 1.3943. Min Range: -1.3943

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1128701 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.9435. Min Act: -0.0000

Data Index: 307029 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.9196. Min Act: -0.0000

Data Index: 698376 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.9091. Min Act: -0.0000

Data Index: 816301 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.8347. Min Act: -0.0000

Data Index: 178136 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.9326. Min Act: -0.0000

Data Index: 420857 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.8319. Min Act: -0.0000

Data Index: 1155626 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.8890. Min Act: -0.0000

Data Index: 261335 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.8583. Min Act: -0.0000

Data Index: 598542 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7675. Min Act: -0.0000

Data Index: 407931 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7660. Min Act: -0.0000

Data Index: 313415 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1113561 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1319940 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7354. Min Act: -0.0000

Data Index: 650979 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1096948 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.6713. Min Act: -0.0000

Data Index: 874948 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.3943. Min Range: -1.3943

Max Act: 0.6447. Min Act: -0.0000

Data Index: 926736 (C4 (Web Text))

Max Activating Token Index: 216