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

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

Neuron 2157 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5931. Min Range: -2.5931

Max Act: 2.5931. Min Act: -0.0000

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 2.5931. Min Range: -2.5931

Max Act: 2.1475. Min Act: -0.0001

Data Index: 1131249 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.8064. Min Act: -0.0000

Data Index: 672840 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 2.5931. Min Range: -2.5931

Max Act: 2.0834. Min Act: -0.0000

Data Index: 1358209 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.9663. Min Act: -0.0000

Data Index: 1202937 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 2.5931. Min Range: -2.5931

Max Act: 2.0337. Min Act: -0.0000

Data Index: 813055 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.9338. Min Act: -0.0001

Data Index: 728473 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.9070. Min Act: -0.0001

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.8089. Min Act: -0.0001

Data Index: 980675 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.9053. Min Act: -0.0001

Data Index: 265557 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.8864. Min Act: -0.0001

Data Index: 1197097 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.7906. Min Act: -0.0001

Data Index: 1262800 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.8183. Min Act: -0.0001

Data Index: 115609 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.6959. Min Act: -0.0000

Data Index: 1172713 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.9693. Min Act: -0.0001

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.7175. Min Act: -0.0000

Data Index: 615993 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.8129. Min Act: -0.0000

Data Index: 419301 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.6121. Min Act: -0.0000

Data Index: 106391 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.6962. Min Act: -0.0001

Data Index: 528668 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 2.5931. Min Range: -2.5931

Max Act: 1.5999. Min Act: -0.0000

Data Index: 385276 (C4 (Web Text))

Max Activating Token Index: 616