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

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

Neuron 2500 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0001

Data Index: 960671 (C4 (Web Text))

Max Activating Token Index: 922

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1067155 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1326. Min Act: -0.0001

Data Index: 754485 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1296. Min Act: -0.0001

Data Index: 1142491 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1312. Min Act: -0.0001

Data Index: 658452 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1299. Min Act: -0.0001

Data Index: 247342 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1141. Min Act: -0.0001

Data Index: 573396 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1161. Min Act: -0.0001

Data Index: 15118 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1143. Min Act: -0.0001

Data Index: 746601 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0998. Min Act: -0.0001

Data Index: 374817 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1089123 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1024. Min Act: -0.0001

Data Index: 592787 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0968. Min Act: -0.0001

Data Index: 546230 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0997. Min Act: -0.0001

Data Index: 361047 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1321150 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0999. Min Act: -0.0001

Data Index: 250281 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0956. Min Act: -0.0001

Data Index: 592888 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0991. Min Act: -0.0001

Data Index: 286396 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0959. Min Act: -0.0001

Data Index: 1289437 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0875. Min Act: -0.0001

Data Index: 212008 (C4 (Web Text))

Max Activating Token Index: 808