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

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

Neuron 3105 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4932. Min Act: -0.0000

Data Index: 175122 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.4081. Min Act: 0.0000

Data Index: 1049409 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3614. Min Act: -0.0000

Data Index: 510571 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3686. Min Act: 0.0000

Data Index: 701183 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3318. Min Act: -0.0000

Data Index: 670545 (C4 (Web Text))

Max Activating Token Index: 284

Text #5

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3199. Min Act: -0.0000

Data Index: 893648 (C4 (Web Text))

Max Activating Token Index: 376

Text #6

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3095. Min Act: -0.0000

Data Index: 580062 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3081. Min Act: 0.0000

Data Index: 378917 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3022. Min Act: -0.0000

Data Index: 615684 (C4 (Web Text))

Max Activating Token Index: 110

Text #9

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1087049 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.3071. Min Act: 0.0001

Data Index: 770185 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2983. Min Act: -0.0000

Data Index: 502197 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2778. Min Act: -0.0000

Data Index: 121355 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2844. Min Act: -0.0000

Data Index: 388862 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2747. Min Act: -0.0000

Data Index: 481624 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2696. Min Act: -0.0000

Data Index: 937503 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2779. Min Act: -0.0000

Data Index: 69468 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1215203 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2708. Min Act: -0.0000

Data Index: 186803 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.4932. Min Range: -0.4932

Max Act: 0.2610. Min Act: -0.0000

Data Index: 905673 (C4 (Web Text))

Max Activating Token Index: 226