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

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

Neuron 2195 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: 0.4282. Min Range: -0.4282

Max Act: 0.4282. Min Act: -0.0001

Data Index: 78750 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3880. Min Act: -0.0001

Data Index: 886016 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3864. Min Act: -0.0002

Data Index: 62413 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3789. Min Act: -0.0001

Data Index: 1328440 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3565. Min Act: -0.0001

Data Index: 147286 (C4 (Web Text))

Max Activating Token Index: 46

Text #5

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3556. Min Act: -0.0001

Data Index: 795102 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3505. Min Act: -0.0001

Data Index: 1132229 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3490. Min Act: -0.0001

Data Index: 104109 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3396. Min Act: -0.0001

Data Index: 935906 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3370. Min Act: -0.0001

Data Index: 746646 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1222023 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3322. Min Act: -0.0001

Data Index: 399367 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3309. Min Act: -0.0001

Data Index: 800962 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3318. Min Act: -0.0001

Data Index: 13411 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3274. Min Act: -0.0002

Data Index: 1188624 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3329. Min Act: -0.0002

Data Index: 1174490 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3293. Min Act: -0.0001

Data Index: 630194 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3306. Min Act: -0.0002

Data Index: 501421 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3255. Min Act: -0.0001

Data Index: 28943 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3262. Min Act: -0.0001

Data Index: 676107 (C4 (Web Text))

Max Activating Token Index: 448