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

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

Neuron 2870 in Layer 1

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: 2.0266. Min Range: -2.0266

Max Act: 2.0266. Min Act: -0.0003

Data Index: 612551 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.8183. Min Act: -0.0002

Data Index: 68992 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.8261. Min Act: -0.0002

Data Index: 973293 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7802. Min Act: -0.0002

Data Index: 597800 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7352. Min Act: -0.0002

Data Index: 1267727 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7541. Min Act: -0.0003

Data Index: 192589 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7307. Min Act: -0.0002

Data Index: 849564 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7250. Min Act: -0.0002

Data Index: 756384 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7038. Min Act: -0.0002

Data Index: 647895 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7054. Min Act: -0.0002

Data Index: 936640 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.7472. Min Act: -0.0003

Data Index: 191375 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6823. Min Act: -0.0002

Data Index: 326722 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6941. Min Act: -0.0002

Data Index: 198351 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6805. Min Act: -0.0002

Data Index: 1321985 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6410. Min Act: -0.0002

Data Index: 147825 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6542. Min Act: -0.0002

Data Index: 654734 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6578. Min Act: -0.0002

Data Index: 826852 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6279. Min Act: -0.0002

Data Index: 361342 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6239. Min Act: -0.0002

Data Index: 781897 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 2.0266. Min Range: -2.0266

Max Act: 1.6137. Min Act: -0.0002

Data Index: 989018 (C4 (Web Text))

Max Activating Token Index: 132