Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3288 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3939. Min Act: -0.0001

Data Index: 356548 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3294. Min Act: -0.0000

Data Index: 566577 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3064. Min Act: -0.0000

Data Index: 428169 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3138. Min Act: -0.0000

Data Index: 833702 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3080. Min Act: -0.0000

Data Index: 271126 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3195. Min Act: -0.0000

Data Index: 810778 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3159. Min Act: -0.0000

Data Index: 448478 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2920. Min Act: -0.0001

Data Index: 1017021 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2934. Min Act: -0.0000

Data Index: 767535 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3217. Min Act: -0.0000

Data Index: 607001 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.3023. Min Act: -0.0001

Data Index: 1039988 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2822. Min Act: -0.0000

Data Index: 710005 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2993. Min Act: -0.0001

Data Index: 575833 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2701. Min Act: -0.0000

Data Index: 587636 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2788. Min Act: -0.0000

Data Index: 581182 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2866. Min Act: -0.0001

Data Index: 495736 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1090194 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2918. Min Act: -0.0001

Data Index: 369422 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1023766 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.3939. Min Range: -0.3939

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1232782 (C4 (Web Text))

Max Activating Token Index: 946