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

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

Neuron 2944 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: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0001

Data Index: 895501 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0365. Min Act: -0.0001

Data Index: 959501 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0365. Min Act: -0.0001

Data Index: 1177113 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0366. Min Act: -0.0001

Data Index: 220843 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0357. Min Act: -0.0001

Data Index: 1352306 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0350. Min Act: -0.0001

Data Index: 604828 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0360. Min Act: -0.0001

Data Index: 277539 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0351. Min Act: -0.0001

Data Index: 495719 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0356. Min Act: -0.0001

Data Index: 57466 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0350. Min Act: -0.0001

Data Index: 727235 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0346. Min Act: -0.0001

Data Index: 811210 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0340. Min Act: -0.0001

Data Index: 718189 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0346. Min Act: -0.0001

Data Index: 1199104 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0340. Min Act: -0.0001

Data Index: 489666 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0338. Min Act: -0.0001

Data Index: 345660 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0336. Min Act: -0.0001

Data Index: 590246 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1114812 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0333. Min Act: -0.0001

Data Index: 722074 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0333. Min Act: -0.0001

Data Index: 243374 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1218158 (C4 (Web Text))

Max Activating Token Index: 839