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

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

Neuron 2826 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.4733. Min Act: -0.0001

Data Index: 1113596 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.6183. Min Act: -0.0001

Data Index: 562160 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.4722. Min Act: -0.0001

Data Index: 1145384 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2300. Min Act: -0.0001

Data Index: 773471 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2653. Min Act: -0.0001

Data Index: 804623 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2873. Min Act: -0.0001

Data Index: 758878 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1515. Min Act: -0.0001

Data Index: 141369 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2138. Min Act: -0.0001

Data Index: 462418 (C4 (Web Text))

Max Activating Token Index: 997

Text #8

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2651. Min Act: -0.0001

Data Index: 753251 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2243. Min Act: -0.0001

Data Index: 402169 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1616. Min Act: -0.0001

Data Index: 1005306 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1918. Min Act: -0.0001

Data Index: 152824 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.6183. Min Range: -1.6183

Max Act: 0.9946. Min Act: -0.0001

Data Index: 201609 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1569. Min Act: -0.0001

Data Index: 496038 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2136. Min Act: -0.0001

Data Index: 576700 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1320. Min Act: -0.0001

Data Index: 90661 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.0277. Min Act: -0.0001

Data Index: 1006741 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.1595. Min Act: -0.0001

Data Index: 1289391 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.2737. Min Act: -0.0001

Data Index: 1141017 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 1.6183. Min Range: -1.6183

Max Act: 1.0469. Min Act: -0.0001

Data Index: 421998 (C4 (Web Text))

Max Activating Token Index: 194