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

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

Neuron 2495 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.4046. Min Act: -0.0001

Data Index: 417819 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.3257. Min Act: -0.0001

Data Index: 468139 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.3114. Min Act: -0.0001

Data Index: 1256585 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2750. Min Act: -0.0001

Data Index: 473905 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2948. Min Act: -0.0001

Data Index: 980384 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2939. Min Act: -0.0001

Data Index: 351790 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2849. Min Act: -0.0001

Data Index: 922089 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2852. Min Act: -0.0001

Data Index: 572960 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2953. Min Act: -0.0001

Data Index: 1038619 (C4 (Web Text))

Max Activating Token Index: 1013

Text #9

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2927. Min Act: -0.0001

Data Index: 949974 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2940. Min Act: -0.0001

Data Index: 955140 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2518. Min Act: -0.0001

Data Index: 85881 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2743. Min Act: -0.0001

Data Index: 885030 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2669. Min Act: -0.0001

Data Index: 299217 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2576. Min Act: -0.0001

Data Index: 27527 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2626. Min Act: -0.0001

Data Index: 992877 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2228. Min Act: -0.0001

Data Index: 157921 (C4 (Web Text))

Max Activating Token Index: 1016

Text #17

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2366. Min Act: -0.0001

Data Index: 737454 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2538. Min Act: -0.0001

Data Index: 413613 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.4046. Min Range: -0.4046

Max Act: 0.2321. Min Act: -0.0001

Data Index: 1366719 (Python Code)

Max Activating Token Index: 261