Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 146 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.9741. Min Act: -0.0001

Data Index: 1392144 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1369364 (Python Code)

Max Activating Token Index: 944

Text #2

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8112. Min Act: -0.0000

Data Index: 926648 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7582. Min Act: -0.0000

Data Index: 561672 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8046. Min Act: -0.0000

Data Index: 34504 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.8013. Min Act: -0.0000

Data Index: 541456 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1004459 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7532. Min Act: -0.0000

Data Index: 73192 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7470. Min Act: -0.0000

Data Index: 242095 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7483. Min Act: -0.0000

Data Index: 510739 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1025389 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.6852. Min Act: -0.0000

Data Index: 666978 (C4 (Web Text))

Max Activating Token Index: 304

Text #12

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7297. Min Act: -0.0000

Data Index: 1309861 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7231. Min Act: -0.0000

Data Index: 429170 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7186. Min Act: -0.0000

Data Index: 661433 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7186. Min Act: -0.0000

Data Index: 79290 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1196502 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7641. Min Act: -0.0000

Data Index: 547405 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7137. Min Act: -0.0000

Data Index: 801460 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.9741. Min Range: -0.9741

Max Act: 0.7793. Min Act: -0.0000

Data Index: 716455 (C4 (Web Text))

Max Activating Token Index: 823