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

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

Neuron 589 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: 0.1286. Min Range: -0.1286

Max Act: 0.1231. Min Act: -0.0001

Data Index: 764002 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1286. Min Act: -0.0001

Data Index: 188710 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1599285 (Python Code)

Max Activating Token Index: 366

Text #3

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1134. Min Act: -0.0001

Data Index: 1383917 (Python Code)

Max Activating Token Index: 1003

Text #4

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1160. Min Act: -0.0002

Data Index: 867438 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1601348 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1554093 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1076. Min Act: -0.0002

Data Index: 726963 (C4 (Web Text))

Max Activating Token Index: 132

Text #8

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1052. Min Act: -0.0001

Data Index: 21064 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1462471 (Python Code)

Max Activating Token Index: 227

Text #10

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1571562 (Python Code)

Max Activating Token Index: 133

Text #11

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1068. Min Act: -0.0002

Data Index: 963784 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1026. Min Act: -0.0002

Data Index: 824186 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1486689 (Python Code)

Max Activating Token Index: 760

Text #14

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1007. Min Act: -0.0001

Data Index: 1642809 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0973. Min Act: -0.0002

Data Index: 342950 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1499142 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1516769 (Python Code)

Max Activating Token Index: 367

Text #18

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.0950. Min Act: -0.0002

Data Index: 96020 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.1286. Min Range: -0.1286

Max Act: 0.1024. Min Act: -0.0001

Data Index: 442373 (C4 (Web Text))

Max Activating Token Index: 709