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

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

Neuron 4294 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: 0.6135. Min Range: -0.6135

Max Act: 0.6135. Min Act: -0.0002

Data Index: 1140301 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.6037. Min Act: -0.0002

Data Index: 1049621 (C4 (Web Text))

Max Activating Token Index: 12

Text #2

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5542. Min Act: -0.0002

Data Index: 549898 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5595. Min Act: -0.0002

Data Index: 380151 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5607. Min Act: -0.0002

Data Index: 1159774 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5534. Min Act: -0.0002

Data Index: 49155 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5506. Min Act: -0.0003

Data Index: 1311364 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5485. Min Act: -0.0002

Data Index: 999680 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5410. Min Act: -0.0003

Data Index: 505140 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5417. Min Act: -0.0002

Data Index: 167514 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5448. Min Act: -0.0003

Data Index: 310207 (C4 (Web Text))

Max Activating Token Index: 15

Text #11

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5421. Min Act: -0.0002

Data Index: 442295 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5341. Min Act: -0.0002

Data Index: 1128037 (C4 (Web Text))

Max Activating Token Index: 16

Text #13

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5412. Min Act: -0.0002

Data Index: 1269963 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5461. Min Act: -0.0002

Data Index: 264271 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5358. Min Act: -0.0002

Data Index: 853686 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5196. Min Act: -0.0002

Data Index: 1137796 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5236. Min Act: -0.0002

Data Index: 712064 (C4 (Web Text))

Max Activating Token Index: 393

Text #18

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5253. Min Act: -0.0002

Data Index: 502296 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.6135. Min Range: -0.6135

Max Act: 0.5386. Min Act: -0.0002

Data Index: 1312882 (C4 (Web Text))

Max Activating Token Index: 4