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

Dataset: The Pile

Neuron 39 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2835. Min Act: -0.0000

Data Index: 272407 (The Pile)

Max Activating Token Index: 803

Text #1

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1028348 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2932. Min Act: -0.0000

Data Index: 314298 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2900. Min Act: -0.0000

Data Index: 931224 (The Pile)

Max Activating Token Index: 544

Text #4

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2875. Min Act: -0.0000

Data Index: 585772 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1709553 (The Pile)

Max Activating Token Index: 240

Text #6

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2499. Min Act: -0.0000

Data Index: 472160 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1029186 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2506. Min Act: -0.0000

Data Index: 693656 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2389. Min Act: -0.0000

Data Index: 1092169 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2292. Min Act: -0.0000

Data Index: 1086800 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1822. Min Act: -0.0000

Data Index: 217072 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1369743 (The Pile)

Max Activating Token Index: 901

Text #13

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1479302 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1586114 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1051079 (The Pile)

Max Activating Token Index: 213

Text #16

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2100. Min Act: -0.0000

Data Index: 510918 (The Pile)

Max Activating Token Index: 25

Text #17

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1508813 (The Pile)

Max Activating Token Index: 203

Text #18

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.1949. Min Act: -0.0000

Data Index: 787900 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.3080. Min Range: -0.3080

Max Act: 0.2236. Min Act: -0.0000

Data Index: 529702 (The Pile)

Max Activating Token Index: 711