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

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

Neuron 1346 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: 0.7960. Min Range: -0.7960

Max Act: 0.7960. Min Act: -0.0000

Data Index: 849582 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6757. Min Act: -0.0000

Data Index: 194355 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6103. Min Act: -0.0000

Data Index: 725635 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6099. Min Act: -0.0001

Data Index: 928976 (C4 (Web Text))

Max Activating Token Index: 852

Text #4

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6084. Min Act: -0.0000

Data Index: 209435 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6085. Min Act: -0.0000

Data Index: 848479 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6090. Min Act: -0.0000

Data Index: 624385 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5876. Min Act: -0.0000

Data Index: 898085 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.6070. Min Act: -0.0000

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5566. Min Act: -0.0000

Data Index: 575351 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5509. Min Act: -0.0000

Data Index: 244222 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5558. Min Act: -0.0000

Data Index: 673053 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5310. Min Act: -0.0000

Data Index: 856434 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5107. Min Act: -0.0000

Data Index: 707026 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5252. Min Act: -0.0001

Data Index: 1314084 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5211. Min Act: -0.0001

Data Index: 983109 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4992. Min Act: -0.0000

Data Index: 686647 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1074597 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1260474 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.7960. Min Range: -0.7960

Max Act: 0.4926. Min Act: -0.0000

Data Index: 171989 (C4 (Web Text))

Max Activating Token Index: 284