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

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

Neuron 3409 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2311. Min Range: -1.2311

Max Act: 1.2311. Min Act: -0.0001

Data Index: 764374 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.7157. Min Act: -0.0001

Data Index: 1145261 (C4 (Web Text))

Max Activating Token Index: 126

Text #2

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.6835. Min Act: -0.0001

Data Index: 713000 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.6283. Min Act: -0.0001

Data Index: 199903 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5992. Min Act: -0.0001

Data Index: 338008 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5329. Min Act: -0.0001

Data Index: 549407 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5629. Min Act: -0.0001

Data Index: 1170219 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4793. Min Act: -0.0001

Data Index: 547867 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5250. Min Act: -0.0001

Data Index: 471195 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5148. Min Act: -0.0001

Data Index: 739354 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4671. Min Act: -0.0001

Data Index: 469728 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5508. Min Act: -0.0001

Data Index: 1272938 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.6303. Min Act: -0.0001

Data Index: 1837 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5320. Min Act: -0.0001

Data Index: 237278 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.5442. Min Act: -0.0000

Data Index: 789931 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4250. Min Act: -0.0001

Data Index: 366981 (C4 (Web Text))

Max Activating Token Index: 978

Text #16

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4661. Min Act: -0.0001

Data Index: 971786 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4362. Min Act: -0.0001

Data Index: 939243 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4576. Min Act: -0.0001

Data Index: 801098 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 1.2311. Min Range: -1.2311

Max Act: 0.4593. Min Act: -0.0001

Data Index: 1320849 (C4 (Web Text))

Max Activating Token Index: 644