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

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

Neuron 335 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: 0.4951. Min Range: -0.4951

Max Act: 0.4951. Min Act: -0.0000

Data Index: 111975 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4552. Min Act: 0.0000

Data Index: 1187033 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1095084 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4168. Min Act: -0.0000

Data Index: 570433 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4112. Min Act: -0.0000

Data Index: 419640 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3920. Min Act: -0.0000

Data Index: 289977 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4041. Min Act: -0.0000

Data Index: 264654 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3744. Min Act: -0.0000

Data Index: 727483 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.4012. Min Act: -0.0000

Data Index: 420413 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3831. Min Act: 0.0001

Data Index: 467661 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3885. Min Act: -0.0000

Data Index: 292888 (C4 (Web Text))

Max Activating Token Index: 319

Text #11

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3602. Min Act: 0.0001

Data Index: 68415 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3706. Min Act: -0.0000

Data Index: 775960 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3544. Min Act: -0.0001

Data Index: 461920 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3606. Min Act: 0.0001

Data Index: 386296 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3606. Min Act: 0.0001

Data Index: 1296241 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1286472 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3440. Min Act: -0.0000

Data Index: 451698 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1353855 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.4951. Min Range: -0.4951

Max Act: 0.3535. Min Act: 0.0001

Data Index: 311448 (C4 (Web Text))

Max Activating Token Index: 254