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

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

Neuron 1186 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.2380. Min Act: -0.0001

Data Index: 330530 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.1761. Min Act: -0.0001

Data Index: 1212716 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.1216. Min Act: -0.0001

Data Index: 562514 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0211. Min Act: -0.0001

Data Index: 1408634 (Python Code)

Max Activating Token Index: 249

Text #4

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0624. Min Act: -0.0001

Data Index: 554653 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9849. Min Act: -0.0001

Data Index: 559163 (C4 (Web Text))

Max Activating Token Index: 970

Text #6

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8436. Min Act: -0.0001

Data Index: 1494544 (Python Code)

Max Activating Token Index: 924

Text #7

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0641. Min Act: -0.0001

Data Index: 1023882 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9963. Min Act: -0.0001

Data Index: 1544681 (Python Code)

Max Activating Token Index: 915

Text #9

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9547. Min Act: -0.0001

Data Index: 1310257 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9665. Min Act: -0.0001

Data Index: 21705 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9971. Min Act: -0.0001

Data Index: 158483 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9917. Min Act: -0.0001

Data Index: 994620 (C4 (Web Text))

Max Activating Token Index: 854

Text #13

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9354. Min Act: -0.0001

Data Index: 807953 (C4 (Web Text))

Max Activating Token Index: 287

Text #14

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9204. Min Act: -0.0001

Data Index: 1019845 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9095. Min Act: -0.0001

Data Index: 283610 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1050056 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9688. Min Act: -0.0001

Data Index: 454379 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 1.2380. Min Range: -1.2380

Max Act: 1.0256. Min Act: -0.0001

Data Index: 248781 (C4 (Web Text))

Max Activating Token Index: 204

Text #19

Max Range: 1.2380. Min Range: -1.2380

Max Act: 0.9582. Min Act: -0.0001

Data Index: 892942 (C4 (Web Text))

Max Activating Token Index: 128