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

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

Neuron 1153 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: 0.4953. Min Range: -0.4953

Max Act: 0.4670. Min Act: -0.0000

Data Index: 795058 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4953. Min Act: -0.0000

Data Index: 1182447 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4414. Min Act: -0.0000

Data Index: 972205 (C4 (Web Text))

Max Activating Token Index: 854

Text #3

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4676. Min Act: -0.0000

Data Index: 754042 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4794. Min Act: -0.0000

Data Index: 1076354 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4009. Min Act: -0.0000

Data Index: 816541 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.4239. Min Act: -0.0000

Data Index: 701178 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3928. Min Act: -0.0000

Data Index: 853026 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3844. Min Act: -0.0000

Data Index: 5344 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3632. Min Act: -0.0000

Data Index: 1238817 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3578. Min Act: -0.0000

Data Index: 765435 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3120. Min Act: -0.0000

Data Index: 746470 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3487. Min Act: -0.0000

Data Index: 894324 (C4 (Web Text))

Max Activating Token Index: 127

Text #13

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3662. Min Act: -0.0000

Data Index: 268656 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3293. Min Act: -0.0000

Data Index: 118078 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3483. Min Act: -0.0000

Data Index: 564131 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3241. Min Act: -0.0000

Data Index: 807050 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3097. Min Act: -0.0000

Data Index: 240860 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3048. Min Act: -0.0000

Data Index: 285652 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.4953. Min Range: -0.4953

Max Act: 0.3335. Min Act: -0.0000

Data Index: 456802 (C4 (Web Text))

Max Activating Token Index: 512