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

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

Neuron 5351 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: 1.0558. Min Range: -1.0558

Max Act: 1.0558. Min Act: -0.0000

Data Index: 660039 (C4 (Web Text))

Max Activating Token Index: 148

Text #1

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.9513. Min Act: -0.0000

Data Index: 901105 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.9927. Min Act: -0.0000

Data Index: 531977 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.8978. Min Act: -0.0000

Data Index: 545095 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7934. Min Act: -0.0000

Data Index: 213165 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7926. Min Act: -0.0000

Data Index: 180356 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.8168. Min Act: -0.0000

Data Index: 829919 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1034808 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7969. Min Act: -0.0000

Data Index: 558400 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.8427. Min Act: -0.0000

Data Index: 121407 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7828. Min Act: -0.0000

Data Index: 188217 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7373. Min Act: -0.0000

Data Index: 468708 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1300071 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7117. Min Act: -0.0000

Data Index: 892834 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.6782. Min Act: -0.0000

Data Index: 1018277 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.6741. Min Act: -0.0000

Data Index: 244459 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7632. Min Act: -0.0000

Data Index: 399069 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.6920. Min Act: -0.0000

Data Index: 465268 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.7289. Min Act: -0.0000

Data Index: 858125 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.0558. Min Range: -1.0558

Max Act: 0.6212. Min Act: -0.0000

Data Index: 79027 (C4 (Web Text))

Max Activating Token Index: 856