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

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

Neuron 1347 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3686. Min Act: -0.0000

Data Index: 11487 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3069. Min Act: -0.0000

Data Index: 703071 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3162. Min Act: -0.0000

Data Index: 513998 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3157. Min Act: -0.0000

Data Index: 451684 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3108. Min Act: -0.0000

Data Index: 197045 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3015. Min Act: -0.0000

Data Index: 1150412 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2953. Min Act: -0.0000

Data Index: 467555 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2861. Min Act: -0.0000

Data Index: 29036 (C4 (Web Text))

Max Activating Token Index: 393

Text #8

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3002. Min Act: -0.0000

Data Index: 717207 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2963. Min Act: -0.0000

Data Index: 80688 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2984. Min Act: -0.0000

Data Index: 349678 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2777. Min Act: -0.0000

Data Index: 683124 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2749. Min Act: -0.0000

Data Index: 965090 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2827. Min Act: -0.0000

Data Index: 779023 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.3029. Min Act: -0.0000

Data Index: 81287 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2809. Min Act: -0.0000

Data Index: 990215 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2825. Min Act: -0.0000

Data Index: 493119 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2854. Min Act: 0.0001

Data Index: 535909 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2733. Min Act: -0.0000

Data Index: 347170 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.3686. Min Range: -0.3686

Max Act: 0.2825. Min Act: -0.0000

Data Index: 463376 (C4 (Web Text))

Max Activating Token Index: 945