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

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

Neuron 510 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2405. Min Act: -0.0001

Data Index: 462516 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2168. Min Act: -0.0001

Data Index: 1354902 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2359. Min Act: -0.0001

Data Index: 1015110 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2265. Min Act: -0.0001

Data Index: 18861 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2151. Min Act: -0.0001

Data Index: 543567 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2079. Min Act: -0.0001

Data Index: 1060936 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2179. Min Act: -0.0001

Data Index: 304082 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2251. Min Act: -0.0001

Data Index: 1104685 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2117. Min Act: -0.0001

Data Index: 143029 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2126. Min Act: -0.0001

Data Index: 1328108 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1978. Min Act: -0.0001

Data Index: 978134 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2137. Min Act: -0.0001

Data Index: 883903 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2076. Min Act: -0.0001

Data Index: 853340 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1044731 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2051. Min Act: -0.0001

Data Index: 1171272 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1994. Min Act: -0.0001

Data Index: 1039392 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1918. Min Act: -0.0001

Data Index: 1247191 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.2001. Min Act: -0.0001

Data Index: 117535 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1964. Min Act: -0.0001

Data Index: 773128 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 0.2405. Min Range: -0.2405

Max Act: 0.1905. Min Act: -0.0001

Data Index: 893117 (C4 (Web Text))

Max Activating Token Index: 11