Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3303 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.5954. Min Act: -0.0000

Data Index: 1015998 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4948. Min Act: -0.0000

Data Index: 406774 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.5458. Min Act: -0.0000

Data Index: 411209 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1046518 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4603. Min Act: -0.0000

Data Index: 55356 (C4 (Web Text))

Max Activating Token Index: 853

Text #5

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2489. Min Act: -0.0000

Data Index: 835951 (C4 (Web Text))

Max Activating Token Index: 317

Text #6

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.4230. Min Act: -0.0000

Data Index: 408712 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9837. Min Act: -0.0000

Data Index: 680621 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2065. Min Act: -0.0000

Data Index: 359994 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2276. Min Act: -0.0000

Data Index: 152097 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2128. Min Act: -0.0000

Data Index: 756157 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1081480 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2702. Min Act: -0.0000

Data Index: 1078859 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1645. Min Act: -0.0000

Data Index: 1110026 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1170. Min Act: -0.0000

Data Index: 703491 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1897. Min Act: -0.0000

Data Index: 113198 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.2464. Min Act: -0.0000

Data Index: 89052 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.1688. Min Act: -0.0000

Data Index: 376361 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 1.5954. Min Range: -1.5954

Max Act: 1.0972. Min Act: -0.0000

Data Index: 377745 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 1.5954. Min Range: -1.5954

Max Act: 0.9931. Min Act: -0.0000

Data Index: 224247 (C4 (Web Text))

Max Activating Token Index: 280