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

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

Neuron 2357 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1314309 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1117813 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7085. Min Act: -0.0001

Data Index: 806086 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6967. Min Act: -0.0001

Data Index: 282889 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6445. Min Act: -0.0001

Data Index: 737355 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6372. Min Act: -0.0001

Data Index: 854950 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6514. Min Act: -0.0001

Data Index: 906211 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6007. Min Act: -0.0001

Data Index: 454071 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6068. Min Act: -0.0001

Data Index: 740510 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5848. Min Act: -0.0001

Data Index: 1029281 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5803. Min Act: -0.0001

Data Index: 155490 (C4 (Web Text))

Max Activating Token Index: 163

Text #11

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5959. Min Act: -0.0001

Data Index: 870682 (C4 (Web Text))

Max Activating Token Index: 814

Text #12

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5602. Min Act: -0.0001

Data Index: 637297 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5745. Min Act: -0.0001

Data Index: 120389 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1071345 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5572. Min Act: -0.0001

Data Index: 32407 (C4 (Web Text))

Max Activating Token Index: 719

Text #16

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5729. Min Act: -0.0001

Data Index: 416870 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5428. Min Act: -0.0001

Data Index: 1306523 (C4 (Web Text))

Max Activating Token Index: 339

Text #18

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5615. Min Act: -0.0001

Data Index: 1034816 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5660. Min Act: -0.0001

Data Index: 511731 (C4 (Web Text))

Max Activating Token Index: 591