Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1683 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.4462. Min Act: -0.0000

Data Index: 1212883 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.4027. Min Act: -0.0000

Data Index: 1345079 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.2881. Min Act: -0.0000

Data Index: 461208 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.1076. Min Act: -0.0000

Data Index: 851029 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.9743. Min Act: -0.0000

Data Index: 938637 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.9924. Min Act: -0.0000

Data Index: 712605 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8051. Min Act: -0.0000

Data Index: 706236 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.0311. Min Act: -0.0000

Data Index: 599701 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.9505. Min Act: -0.0000

Data Index: 309613 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.9362. Min Act: -0.0000

Data Index: 118262 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 2.4462. Min Range: -2.4462

Max Act: 2.0146. Min Act: -0.0000

Data Index: 862456 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8903. Min Act: -0.0000

Data Index: 42321 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8193. Min Act: -0.0000

Data Index: 1413225 (Python Code)

Max Activating Token Index: 717

Text #13

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.7908. Min Act: -0.0000

Data Index: 987496 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.9057. Min Act: -0.0000

Data Index: 1185788 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8805. Min Act: -0.0000

Data Index: 496938 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1309725 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.7720. Min Act: -0.0000

Data Index: 654457 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.7661. Min Act: -0.0000

Data Index: 103471 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 2.4462. Min Range: -2.4462

Max Act: 1.8582. Min Act: -0.0000

Data Index: 770593 (C4 (Web Text))

Max Activating Token Index: 115