Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.9389. Min Act: -0.0001

Data Index: 898883 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.9930. Min Act: -0.0001

Data Index: 1265960 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8023. Min Act: -0.0001

Data Index: 473073 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8428. Min Act: -0.0001

Data Index: 221859 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1483123 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8573. Min Act: -0.0001

Data Index: 174234 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8028. Min Act: -0.0001

Data Index: 963682 (C4 (Web Text))

Max Activating Token Index: 371

Text #7

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7545. Min Act: -0.0001

Data Index: 1243714 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.9114. Min Act: -0.0001

Data Index: 936336 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7941. Min Act: -0.0001

Data Index: 1343610 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8344. Min Act: -0.0001

Data Index: 637161 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7501. Min Act: -0.0001

Data Index: 1060835 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.8254. Min Act: -0.0001

Data Index: 656990 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7890. Min Act: -0.0001

Data Index: 80312 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7999. Min Act: -0.0001

Data Index: 521991 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7706. Min Act: -0.0001

Data Index: 175965 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.6703. Min Act: -0.0001

Data Index: 696743 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.6873. Min Act: -0.0001

Data Index: 710512 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7366. Min Act: -0.0001

Data Index: 418339 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.9930. Min Range: -0.9930

Max Act: 0.7581. Min Act: -0.0001

Data Index: 79394 (C4 (Web Text))

Max Activating Token Index: 333