Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3008 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0310. Min Act: -0.0001

Data Index: 763808 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0312. Min Act: -0.0001

Data Index: 980615 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0302. Min Act: -0.0001

Data Index: 333664 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0298. Min Act: -0.0002

Data Index: 861117 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0297. Min Act: -0.0001

Data Index: 991328 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1179004 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0290. Min Act: -0.0001

Data Index: 798793 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0289. Min Act: -0.0001

Data Index: 8275 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0285. Min Act: -0.0001

Data Index: 33731 (C4 (Web Text))

Max Activating Token Index: 97

Text #9

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0283. Min Act: -0.0001

Data Index: 100431 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0281. Min Act: -0.0001

Data Index: 301761 (C4 (Web Text))

Max Activating Token Index: 258

Text #11

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0277. Min Act: -0.0001

Data Index: 1304214 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1125312 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0279. Min Act: -0.0001

Data Index: 789328 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0282. Min Act: -0.0001

Data Index: 477753 (C4 (Web Text))

Max Activating Token Index: 103

Text #15

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0280. Min Act: -0.0001

Data Index: 350205 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0283. Min Act: -0.0001

Data Index: 649034 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1174825 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0280. Min Act: -0.0001

Data Index: 63260 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0312. Min Range: -0.0312

Max Act: 0.0280. Min Act: -0.0001

Data Index: 541911 (C4 (Web Text))

Max Activating Token Index: 156