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

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

Neuron 2524 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: 0.4927. Min Range: -0.4927

Max Act: 0.4927. Min Act: -0.0000

Data Index: 486132 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.4573. Min Act: -0.0000

Data Index: 100533 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3728. Min Act: -0.0001

Data Index: 83273 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3672. Min Act: -0.0000

Data Index: 384963 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3409. Min Act: -0.0000

Data Index: 790640 (C4 (Web Text))

Max Activating Token Index: 60

Text #5

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1141422 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3260. Min Act: -0.0000

Data Index: 464509 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3330. Min Act: -0.0000

Data Index: 456210 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3234. Min Act: -0.0001

Data Index: 452532 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1090513 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3780. Min Act: -0.0000

Data Index: 506701 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2957. Min Act: -0.0000

Data Index: 453212 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3291. Min Act: -0.0001

Data Index: 813582 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2982. Min Act: -0.0000

Data Index: 887309 (C4 (Web Text))

Max Activating Token Index: 499

Text #14

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3116. Min Act: -0.0001

Data Index: 334121 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3043. Min Act: -0.0000

Data Index: 858359 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.3037. Min Act: -0.0000

Data Index: 1008723 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2855. Min Act: -0.0000

Data Index: 339752 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2782. Min Act: -0.0001

Data Index: 684385 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.4927. Min Range: -0.4927

Max Act: 0.2574. Min Act: -0.0000

Data Index: 339281 (C4 (Web Text))

Max Activating Token Index: 635