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

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

Neuron 1930 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1338596 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8344. Min Act: -0.0000

Data Index: 376642 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7903. Min Act: -0.0000

Data Index: 874906 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.8023. Min Act: -0.0000

Data Index: 1056519 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7653. Min Act: -0.0000

Data Index: 269017 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7670. Min Act: -0.0000

Data Index: 204986 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7826. Min Act: -0.0001

Data Index: 137976 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7027. Min Act: -0.0001

Data Index: 988164 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7249. Min Act: -0.0001

Data Index: 1286074 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7048. Min Act: -0.0001

Data Index: 476443 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7314. Min Act: -0.0000

Data Index: 893186 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7252. Min Act: -0.0001

Data Index: 64017 (C4 (Web Text))

Max Activating Token Index: 317

Text #12

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1072759 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6721. Min Act: -0.0001

Data Index: 179755 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.7139. Min Act: -0.0000

Data Index: 898934 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6858. Min Act: -0.0000

Data Index: 1035293 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6861. Min Act: -0.0000

Data Index: 667931 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6768. Min Act: -0.0000

Data Index: 727514 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6772. Min Act: -0.0000

Data Index: 1127895 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 0.8453. Min Range: -0.8453

Max Act: 0.6970. Min Act: -0.0001

Data Index: 1274989 (C4 (Web Text))

Max Activating Token Index: 324