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

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

Neuron 989 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.6167. Min Act: -0.0000

Data Index: 702053 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5936. Min Act: -0.0001

Data Index: 1275323 (C4 (Web Text))

Max Activating Token Index: 419

Text #2

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5762. Min Act: -0.0001

Data Index: 299901 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5059. Min Act: -0.0001

Data Index: 232040 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.5189. Min Act: -0.0001

Data Index: 1278800 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4762. Min Act: -0.0001

Data Index: 1009205 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4915. Min Act: -0.0001

Data Index: 764166 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4671. Min Act: -0.0001

Data Index: 551138 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4543. Min Act: -0.0001

Data Index: 1313097 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4403. Min Act: -0.0001

Data Index: 626772 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4722. Min Act: -0.0001

Data Index: 1325338 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4312. Min Act: -0.0001

Data Index: 253288 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4458. Min Act: -0.0001

Data Index: 256783 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4531. Min Act: -0.0001

Data Index: 135403 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4297. Min Act: -0.0000

Data Index: 880827 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4461. Min Act: -0.0000

Data Index: 998797 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1357126 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3472. Min Act: -0.0001

Data Index: 595316 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.3975. Min Act: -0.0001

Data Index: 375887 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.6167. Min Range: -0.6167

Max Act: 0.4073. Min Act: -0.0001

Data Index: 720667 (C4 (Web Text))

Max Activating Token Index: 867