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

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

Neuron 3139 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: 3.1135. Min Range: -3.1135

Max Act: 3.1135. Min Act: -0.0002

Data Index: 1189690 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 3.1135. Min Range: -3.1135

Max Act: 3.0837. Min Act: -0.0002

Data Index: 23410 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.1135. Min Range: -3.1135

Max Act: 3.0444. Min Act: -0.0002

Data Index: 1241550 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 3.1135. Min Range: -3.1135

Max Act: 3.0257. Min Act: -0.0002

Data Index: 1239267 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.9294. Min Act: -0.0002

Data Index: 673235 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.9065. Min Act: -0.0002

Data Index: 159852 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.8865. Min Act: -0.0002

Data Index: 281252 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7398. Min Act: -0.0002

Data Index: 609844 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7867. Min Act: -0.0002

Data Index: 110819 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.8631. Min Act: -0.0002

Data Index: 1074099 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7643. Min Act: -0.0002

Data Index: 627171 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7265. Min Act: -0.0002

Data Index: 673665 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7507. Min Act: -0.0002

Data Index: 688576 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7929. Min Act: -0.0002

Data Index: 1341814 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7963. Min Act: -0.0002

Data Index: 398300 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7876. Min Act: -0.0002

Data Index: 6286 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7458. Min Act: -0.0002

Data Index: 269870 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7033. Min Act: -0.0002

Data Index: 68175 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7841. Min Act: -0.0002

Data Index: 982844 (C4 (Web Text))

Max Activating Token Index: 860

Text #19

Max Range: 3.1135. Min Range: -3.1135

Max Act: 2.7417. Min Act: -0.0002

Data Index: 10910 (C4 (Web Text))

Max Activating Token Index: 799