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

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

Neuron 3173 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: 3.0027. Min Range: -3.0027

Max Act: 3.0027. Min Act: -0.0001

Data Index: 1009919 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.9581. Min Act: -0.0001

Data Index: 1267423 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.9917. Min Act: -0.0001

Data Index: 1227812 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.9088. Min Act: -0.0001

Data Index: 932112 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.8273. Min Act: -0.0001

Data Index: 820709 (C4 (Web Text))

Max Activating Token Index: 5

Text #5

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7628. Min Act: -0.0001

Data Index: 132772 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7970. Min Act: -0.0001

Data Index: 819423 (C4 (Web Text))

Max Activating Token Index: 164

Text #7

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7704. Min Act: -0.0001

Data Index: 368806 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7424. Min Act: -0.0001

Data Index: 481473 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7648. Min Act: -0.0001

Data Index: 152344 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7435. Min Act: -0.0001

Data Index: 15852 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7420. Min Act: -0.0001

Data Index: 1116739 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7491. Min Act: -0.0001

Data Index: 1091951 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7582. Min Act: -0.0001

Data Index: 988766 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7012. Min Act: -0.0001

Data Index: 1203459 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.6887. Min Act: -0.0001

Data Index: 628698 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.6657. Min Act: -0.0001

Data Index: 236656 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.6788. Min Act: -0.0001

Data Index: 1182475 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.6467. Min Act: -0.0001

Data Index: 1321294 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 3.0027. Min Range: -3.0027

Max Act: 2.7020. Min Act: -0.0001

Data Index: 310701 (C4 (Web Text))

Max Activating Token Index: 164