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

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

Neuron 3945 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.3307. Min Act: -0.0001

Data Index: 701377 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2292. Min Act: -0.0001

Data Index: 49194 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2157. Min Act: -0.0001

Data Index: 18972 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2167. Min Act: -0.0001

Data Index: 1223750 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2324. Min Act: -0.0001

Data Index: 334799 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2148. Min Act: -0.0001

Data Index: 497946 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2045. Min Act: -0.0001

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2128. Min Act: -0.0001

Data Index: 1103607 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2182. Min Act: -0.0001

Data Index: 928974 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1923. Min Act: -0.0001

Data Index: 429215 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2086. Min Act: -0.0001

Data Index: 1197814 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1802. Min Act: -0.0001

Data Index: 487344 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2136. Min Act: -0.0001

Data Index: 281256 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1980. Min Act: -0.0001

Data Index: 316616 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2105. Min Act: -0.0001

Data Index: 258878 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2185. Min Act: -0.0001

Data Index: 132788 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1945. Min Act: -0.0001

Data Index: 841438 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2082. Min Act: -0.0001

Data Index: 645931 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.2004. Min Act: -0.0001

Data Index: 100223 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.3307. Min Range: -0.3307

Max Act: 0.1979. Min Act: -0.0001

Data Index: 40491 (C4 (Web Text))

Max Activating Token Index: 870