Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2385 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 6.3749. Min Range: -6.3749

Max Act: 6.3749. Min Act: -0.0000

Data Index: 752975 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.5367. Min Act: -0.0001

Data Index: 1108236 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.6142. Min Act: -0.0001

Data Index: 738190 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.1806. Min Act: -0.0000

Data Index: 1263596 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.1303. Min Act: -0.0000

Data Index: 313053 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.2935. Min Act: -0.0000

Data Index: 1240234 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.7095. Min Act: -0.0000

Data Index: 125563 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.7312. Min Act: -0.0001

Data Index: 301142 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.0239. Min Act: -0.0000

Data Index: 411045 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.4150. Min Act: -0.0000

Data Index: 805886 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.5889. Min Act: -0.0001

Data Index: 1287567 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 6.3749. Min Range: -6.3749

Max Act: 5.1412. Min Act: -0.0001

Data Index: 1069217 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.2511. Min Act: -0.0001

Data Index: 1229087 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.7098. Min Act: -0.0000

Data Index: 112095 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.5832. Min Act: -0.0001

Data Index: 600884 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.8897. Min Act: -0.0000

Data Index: 433478 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.0141. Min Act: -0.0001

Data Index: 60920 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.3910. Min Act: -0.0000

Data Index: 88946 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 6.3749. Min Range: -6.3749

Max Act: 3.8596. Min Act: -0.0001

Data Index: 136435 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 6.3749. Min Range: -6.3749

Max Act: 4.3618. Min Act: -0.0000

Data Index: 329158 (C4 (Web Text))

Max Activating Token Index: 1021