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

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

Neuron 2943 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2469. Min Act: -0.0001

Data Index: 714960 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2278. Min Act: -0.0000

Data Index: 553209 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2302. Min Act: -0.0001

Data Index: 1247561 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2160. Min Act: -0.0001

Data Index: 1084933 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2033. Min Act: -0.0001

Data Index: 499672 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.1126. Min Act: -0.0001

Data Index: 287947 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.1775. Min Act: -0.0001

Data Index: 1179538 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.2100. Min Act: -0.0001

Data Index: 1107575 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0897. Min Act: -0.0001

Data Index: 1356472 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.1889. Min Act: -0.0001

Data Index: 618700 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.1053. Min Act: -0.0001

Data Index: 402256 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0663. Min Act: -0.0001

Data Index: 305751 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0649. Min Act: -0.0001

Data Index: 933316 (C4 (Web Text))

Max Activating Token Index: 161

Text #13

Max Range: 1.2469. Min Range: -1.2469

Max Act: 0.9953. Min Act: -0.0000

Data Index: 503470 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0215. Min Act: -0.0001

Data Index: 521916 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0848. Min Act: -0.0001

Data Index: 410996 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0156. Min Act: -0.0001

Data Index: 240007 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0419. Min Act: -0.0001

Data Index: 1049999 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0308. Min Act: -0.0001

Data Index: 1213928 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.2469. Min Range: -1.2469

Max Act: 1.0255. Min Act: -0.0001

Data Index: 291545 (C4 (Web Text))

Max Activating Token Index: 286