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

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

Neuron 465 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.5341. Min Act: -0.0000

Data Index: 999995 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1335561 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.5157. Min Act: -0.0000

Data Index: 871182 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.5241. Min Act: -0.0000

Data Index: 683700 (C4 (Web Text))

Max Activating Token Index: 535

Text #4

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4949. Min Act: -0.0000

Data Index: 90231 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4932. Min Act: -0.0000

Data Index: 773102 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4831. Min Act: -0.0000

Data Index: 1195566 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4861. Min Act: -0.0000

Data Index: 77005 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4482. Min Act: -0.0000

Data Index: 860837 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4829. Min Act: -0.0001

Data Index: 997743 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1061184 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4553. Min Act: -0.0000

Data Index: 311964 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4665. Min Act: -0.0001

Data Index: 1127582 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4194. Min Act: -0.0000

Data Index: 331405 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4386. Min Act: -0.0000

Data Index: 226058 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4100. Min Act: -0.0001

Data Index: 819383 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4141. Min Act: -0.0000

Data Index: 448449 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.4049. Min Act: -0.0000

Data Index: 205378 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.3870. Min Act: -0.0000

Data Index: 549588 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.5341. Min Range: -0.5341

Max Act: 0.3852. Min Act: -0.0001

Data Index: 284377 (C4 (Web Text))

Max Activating Token Index: 340