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

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

Neuron 3231 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5596. Min Act: -0.0000

Data Index: 95332 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.6531. Min Act: -0.0000

Data Index: 218620 (C4 (Web Text))

Max Activating Token Index: 137

Text #2

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4272. Min Act: -0.0000

Data Index: 917650 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5089. Min Act: -0.0000

Data Index: 1290645 (C4 (Web Text))

Max Activating Token Index: 717

Text #4

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4697. Min Act: -0.0000

Data Index: 1155163 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4605. Min Act: -0.0000

Data Index: 1113285 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.4271. Min Act: -0.0000

Data Index: 91721 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.3925. Min Act: -0.0000

Data Index: 748793 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.2180. Min Act: -0.0000

Data Index: 1018283 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.5507. Min Act: -0.0000

Data Index: 1284873 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.0698. Min Act: -0.0000

Data Index: 441019 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.2235. Min Act: -0.0000

Data Index: 492261 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.1952. Min Act: -0.0000

Data Index: 1066 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.1434. Min Act: -0.0000

Data Index: 244418 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 4.6531. Min Range: -4.6531

Max Act: 3.9680. Min Act: -0.0000

Data Index: 828912 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 4.6531. Min Range: -4.6531

Max Act: 3.9331. Min Act: -0.0000

Data Index: 879303 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.2459. Min Act: -0.0000

Data Index: 52015 (C4 (Web Text))

Max Activating Token Index: 194

Text #17

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.0818. Min Act: -0.0000

Data Index: 695909 (C4 (Web Text))

Max Activating Token Index: 863

Text #18

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.2095. Min Act: -0.0000

Data Index: 840645 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 4.6531. Min Range: -4.6531

Max Act: 4.0422. Min Act: -0.0000

Data Index: 1124118 (C4 (Web Text))

Max Activating Token Index: 405