Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3355 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.4154. Min Act: -0.0000

Data Index: 131149 (C4 (Web Text))

Max Activating Token Index: 328

Text #1

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.4326. Min Act: -0.0000

Data Index: 447620 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3632. Min Act: -0.0000

Data Index: 850276 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3157. Min Act: -0.0000

Data Index: 321356 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2981. Min Act: -0.0000

Data Index: 177244 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2946. Min Act: -0.0000

Data Index: 603615 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2824. Min Act: -0.0000

Data Index: 244623 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2841. Min Act: -0.0000

Data Index: 377645 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.3001. Min Act: -0.0000

Data Index: 723081 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1192601 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2844. Min Act: -0.0000

Data Index: 724814 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2878. Min Act: -0.0000

Data Index: 379818 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2731. Min Act: -0.0000

Data Index: 1004359 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2575. Min Act: -0.0000

Data Index: 432645 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2658. Min Act: -0.0000

Data Index: 927956 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2640. Min Act: -0.0000

Data Index: 1262780 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2369. Min Act: -0.0000

Data Index: 712453 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2648. Min Act: -0.0000

Data Index: 678019 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2437. Min Act: -0.0000

Data Index: 283339 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.4326. Min Range: -0.4326

Max Act: 0.2711. Min Act: -0.0000

Data Index: 219741 (C4 (Web Text))

Max Activating Token Index: 433