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

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

Neuron 4090 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: 1.1179. Min Range: -1.1179

Max Act: 1.1179. Min Act: -0.0000

Data Index: 953218 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9450. Min Act: -0.0000

Data Index: 753313 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9563. Min Act: -0.0000

Data Index: 113405 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8847. Min Act: -0.0000

Data Index: 281507 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9332. Min Act: -0.0000

Data Index: 395173 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.9417. Min Act: -0.0000

Data Index: 1344343 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8685. Min Act: -0.0000

Data Index: 398894 (C4 (Web Text))

Max Activating Token Index: 950

Text #7

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8417. Min Act: -0.0000

Data Index: 1059162 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8032. Min Act: -0.0000

Data Index: 371433 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8241. Min Act: -0.0000

Data Index: 377738 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7897. Min Act: -0.0000

Data Index: 541926 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8318. Min Act: -0.0000

Data Index: 654322 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7858. Min Act: -0.0000

Data Index: 952367 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1292871 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.8233. Min Act: -0.0000

Data Index: 241075 (C4 (Web Text))

Max Activating Token Index: 832

Text #15

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7271. Min Act: -0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 940

Text #16

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7385. Min Act: -0.0000

Data Index: 1325757 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7914. Min Act: -0.0000

Data Index: 824182 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7789. Min Act: -0.0000

Data Index: 339960 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 1.1179. Min Range: -1.1179

Max Act: 0.7762. Min Act: -0.0000

Data Index: 538836 (C4 (Web Text))

Max Activating Token Index: 203