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

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

Neuron 343 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.3225. Min Act: -0.0002

Data Index: 1335291 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2925. Min Act: -0.0002

Data Index: 1197776 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2807. Min Act: -0.0002

Data Index: 681616 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2657. Min Act: -0.0002

Data Index: 1236434 (C4 (Web Text))

Max Activating Token Index: 470

Text #4

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2560. Min Act: -0.0002

Data Index: 1357789 (C4 (Web Text))

Max Activating Token Index: 905

Text #5

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2407. Min Act: -0.0001

Data Index: 328775 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2512. Min Act: -0.0001

Data Index: 964760 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2471. Min Act: -0.0002

Data Index: 509539 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2280. Min Act: -0.0001

Data Index: 91521 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2263. Min Act: -0.0002

Data Index: 1222436 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2146. Min Act: -0.0002

Data Index: 827189 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1943. Min Act: -0.0002

Data Index: 348834 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2129. Min Act: -0.0002

Data Index: 1100915 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2108. Min Act: -0.0002

Data Index: 107461 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1186228 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2048. Min Act: -0.0002

Data Index: 1339172 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2190. Min Act: -0.0002

Data Index: 197171 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2200. Min Act: -0.0001

Data Index: 1191777 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.2024. Min Act: -0.0001

Data Index: 429961 (C4 (Web Text))

Max Activating Token Index: 813

Text #19

Max Range: 0.3225. Min Range: -0.3225

Max Act: 0.1963. Min Act: -0.0001

Data Index: 917094 (C4 (Web Text))

Max Activating Token Index: 728