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

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

Neuron 3385 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.3489. Min Act: -0.0000

Data Index: 85834 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9746. Min Act: -0.0000

Data Index: 1052171 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9529. Min Act: -0.0000

Data Index: 196179 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.7930. Min Act: -0.0000

Data Index: 391568 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9697. Min Act: -0.0000

Data Index: 823488 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 1.3489. Min Range: -1.3489

Max Act: 1.0125. Min Act: -0.0000

Data Index: 461009 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.9710. Min Act: -0.0000

Data Index: 917143 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.8095. Min Act: -0.0000

Data Index: 597791 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.8488. Min Act: -0.0000

Data Index: 1206632 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.7999. Min Act: -0.0000

Data Index: 422460 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.7835. Min Act: -0.0000

Data Index: 933689 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.8418. Min Act: -0.0000

Data Index: 333338 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.8539. Min Act: -0.0000

Data Index: 1019838 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.7108. Min Act: -0.0000

Data Index: 362293 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.6238. Min Act: -0.0000

Data Index: 423414 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1241153 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.6331. Min Act: -0.0000

Data Index: 932766 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.6161. Min Act: -0.0000

Data Index: 630883 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.5541. Min Act: -0.0000

Data Index: 113773 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.3489. Min Range: -1.3489

Max Act: 0.5655. Min Act: -0.0000

Data Index: 3413 (C4 (Web Text))

Max Activating Token Index: 285