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

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

Neuron 3440 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.7953. Min Act: -0.0000

Data Index: 618371 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.2240. Min Act: -0.0000

Data Index: 830483 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.3898. Min Act: -0.0000

Data Index: 12886 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.1955. Min Act: -0.0000

Data Index: 95485 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8396. Min Act: -0.0000

Data Index: 540522 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.9480. Min Act: -0.0000

Data Index: 879959 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 3.7953. Min Range: -3.7953

Max Act: 3.0846. Min Act: -0.0000

Data Index: 1651395 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.9302. Min Act: -0.0000

Data Index: 1545517 (Python Code)

Max Activating Token Index: 222

Text #8

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8966. Min Act: -0.0000

Data Index: 1246649 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.7505. Min Act: -0.0000

Data Index: 1071395 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8799. Min Act: -0.0000

Data Index: 195259 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8868. Min Act: -0.0000

Data Index: 1206094 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8876. Min Act: -0.0000

Data Index: 543050 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.8529. Min Act: -0.0000

Data Index: 953920 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.6403. Min Act: -0.0000

Data Index: 957471 (C4 (Web Text))

Max Activating Token Index: 825

Text #15

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.7631. Min Act: -0.0000

Data Index: 623849 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.9199. Min Act: -0.0000

Data Index: 1590815 (Python Code)

Max Activating Token Index: 965

Text #17

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.7681. Min Act: -0.0000

Data Index: 1464471 (Python Code)

Max Activating Token Index: 136

Text #18

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.6314. Min Act: -0.0000

Data Index: 1267604 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.7953. Min Range: -3.7953

Max Act: 2.9009. Min Act: -0.0000

Data Index: 695021 (C4 (Web Text))

Max Activating Token Index: 997