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

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

Neuron 4026 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: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1137264 (C4 (Web Text))

Max Activating Token Index: 390

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2418. Min Act: -0.0001

Data Index: 356920 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2425. Min Act: -0.0001

Data Index: 404979 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2365. Min Act: -0.0000

Data Index: 26102 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1173786 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1256348 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2151. Min Act: -0.0000

Data Index: 293510 (C4 (Web Text))

Max Activating Token Index: 654

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2053. Min Act: -0.0001

Data Index: 963450 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2020. Min Act: -0.0000

Data Index: 91377 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1925. Min Act: -0.0001

Data Index: 740950 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1939. Min Act: -0.0001

Data Index: 152662 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1858. Min Act: -0.0001

Data Index: 832309 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1870. Min Act: -0.0001

Data Index: 294983 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1799. Min Act: -0.0001

Data Index: 494569 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1882. Min Act: -0.0001

Data Index: 219838 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1292263 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1707. Min Act: -0.0001

Data Index: 287430 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1842. Min Act: -0.0000

Data Index: 442282 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1779. Min Act: -0.0001

Data Index: 69048 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1203010 (C4 (Web Text))

Max Activating Token Index: 692