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

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

Neuron 235 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: 0.8740. Min Range: -0.8740

Max Act: 0.8740. Min Act: -0.0001

Data Index: 382937 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7042. Min Act: -0.0000

Data Index: 973390 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1306753 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5577. Min Act: -0.0000

Data Index: 536476 (C4 (Web Text))

Max Activating Token Index: 644

Text #4

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5055. Min Act: -0.0001

Data Index: 414822 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4728. Min Act: -0.0001

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5000. Min Act: -0.0000

Data Index: 792331 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4817. Min Act: -0.0001

Data Index: 8696 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4616. Min Act: -0.0001

Data Index: 83209 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4362. Min Act: -0.0001

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4459. Min Act: -0.0001

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4589. Min Act: -0.0001

Data Index: 770104 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4400. Min Act: -0.0001

Data Index: 26119 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4166. Min Act: -0.0001

Data Index: 871555 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4392. Min Act: -0.0000

Data Index: 539164 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4374. Min Act: -0.0000

Data Index: 895405 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4381. Min Act: -0.0001

Data Index: 1063419 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1062210 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4671. Min Act: -0.0001

Data Index: 947334 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.4079. Min Act: -0.0001

Data Index: 115166 (C4 (Web Text))

Max Activating Token Index: 836