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

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

Neuron 1295 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.0001

Data Index: 59675 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0555. Min Act: -0.0001

Data Index: 461979 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1070. Min Act: -0.0001

Data Index: 140960 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9527. Min Act: -0.0001

Data Index: 1191344 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1206358 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0046. Min Act: -0.0001

Data Index: 390103 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8586. Min Act: -0.0001

Data Index: 216647 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9855. Min Act: -0.0001

Data Index: 1283368 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9755. Min Act: -0.0001

Data Index: 292450 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8136. Min Act: -0.0001

Data Index: 301092 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8468. Min Act: -0.0001

Data Index: 18612 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8483. Min Act: -0.0001

Data Index: 506100 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8959. Min Act: -0.0001

Data Index: 1290137 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8844. Min Act: -0.0001

Data Index: 119511 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8893. Min Act: -0.0000

Data Index: 26678 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8176. Min Act: -0.0001

Data Index: 150073 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9273. Min Act: -0.0001

Data Index: 737521 (C4 (Web Text))

Max Activating Token Index: 1009

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8983. Min Act: -0.0001

Data Index: 1164078 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8152. Min Act: -0.0001

Data Index: 1094122 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.8610. Min Act: -0.0001

Data Index: 1037763 (C4 (Web Text))

Max Activating Token Index: 301