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

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

Neuron 1978 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0501. Min Act: -0.0003

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0191. Min Act: -0.0003

Data Index: 621816 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0179. Min Act: -0.0003

Data Index: 324508 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0167. Min Act: -0.0003

Data Index: 919136 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0168. Min Act: -0.0003

Data Index: 612034 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0143. Min Act: -0.0003

Data Index: 474152 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0134. Min Act: -0.0003

Data Index: 924831 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0135. Min Act: -0.0003

Data Index: 795954 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0131. Min Act: -0.0003

Data Index: 1601169 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0136. Min Act: -0.0003

Data Index: 7882 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0136. Min Act: -0.0003

Data Index: 655434 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0131. Min Act: -0.0003

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0135. Min Act: -0.0003

Data Index: 364488 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0133. Min Act: -0.0003

Data Index: 401199 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0130. Min Act: -0.0003

Data Index: 1123548 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0129. Min Act: -0.0003

Data Index: 67803 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0129. Min Act: -0.0003

Data Index: 141142 (C4 (Web Text))

Max Activating Token Index: 810

Text #17

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0128. Min Act: -0.0003

Data Index: 931831 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0129. Min Act: -0.0003

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.0501. Min Range: -0.0501

Max Act: 0.0126. Min Act: -0.0003

Data Index: 1280678 (C4 (Web Text))

Max Activating Token Index: 402