Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 508 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0004

Data Index: 991538 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0004

Data Index: 23363 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 75207 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0003

Data Index: 1019395 (C4 (Web Text))

Max Activating Token Index: 1004

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0003

Data Index: 11695 (C4 (Web Text))

Max Activating Token Index: 819

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0003

Data Index: 1164480 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0003

Data Index: 718618 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 887256 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0003

Data Index: 893226 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 876375 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 917166 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0004

Data Index: 696938 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 248743 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0003

Data Index: 1209455 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 730648 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 430020 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0003

Data Index: 413586 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 1446171 (Python Code)

Max Activating Token Index: 701

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0059. Min Act: -0.0004

Data Index: 1306627 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0058. Min Act: -0.0003

Data Index: 130328 (C4 (Web Text))

Max Activating Token Index: 863