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

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

Neuron 178 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4256. Min Act: -0.0000

Data Index: 170401 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.4301. Min Act: -0.0000

Data Index: 321929 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1323650 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1309455 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3849. Min Act: -0.0001

Data Index: 56743 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3513. Min Act: -0.0000

Data Index: 786155 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3474. Min Act: -0.0001

Data Index: 900557 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1160285 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1203714 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3275. Min Act: -0.0000

Data Index: 140216 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3268. Min Act: -0.0000

Data Index: 1097662 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3232. Min Act: -0.0000

Data Index: 560932 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1127596 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2849. Min Act: -0.0001

Data Index: 856930 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3036. Min Act: -0.0000

Data Index: 1154011 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3020. Min Act: -0.0000

Data Index: 556932 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2794. Min Act: -0.0000

Data Index: 404873 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2992. Min Act: -0.0000

Data Index: 717541 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.3060. Min Act: -0.0001

Data Index: 601805 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.4301. Min Range: -0.4301

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1150924 (C4 (Web Text))

Max Activating Token Index: 437