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

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

Neuron 3381 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0979. Min Act: -0.0001

Data Index: 16709 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1020. Min Act: -0.0001

Data Index: 557062 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1053. Min Act: -0.0001

Data Index: 441487 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1070. Min Act: -0.0001

Data Index: 727709 (C4 (Web Text))

Max Activating Token Index: 987

Text #4

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0962. Min Act: -0.0001

Data Index: 381505 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1043557 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1003. Min Act: -0.0001

Data Index: 760255 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1215795 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0963. Min Act: -0.0001

Data Index: 1491947 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0893. Min Act: -0.0001

Data Index: 213150 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1558078 (Python Code)

Max Activating Token Index: 267

Text #11

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0807. Min Act: -0.0000

Data Index: 770378 (C4 (Web Text))

Max Activating Token Index: 348

Text #12

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.1017. Min Act: -0.0001

Data Index: 607063 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0832. Min Act: -0.0000

Data Index: 120320 (C4 (Web Text))

Max Activating Token Index: 459

Text #14

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0896. Min Act: -0.0001

Data Index: 293573 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1055124 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0846. Min Act: -0.0001

Data Index: 423470 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1177089 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0841. Min Act: -0.0001

Data Index: 769230 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.1070. Min Range: -0.1070

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1237028 (C4 (Web Text))

Max Activating Token Index: 411