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

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

Neuron 3668 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.4673. Min Act: -0.0001

Data Index: 1258821 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.3849. Min Act: -0.0001

Data Index: 1187261 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.4296. Min Act: -0.0001

Data Index: 236606 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.1107. Min Act: -0.0001

Data Index: 1263523 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.2515. Min Act: -0.0001

Data Index: 863427 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 3.4673. Min Range: -3.4673

Max Act: 3.0162. Min Act: -0.0001

Data Index: 1011763 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.9780. Min Act: -0.0001

Data Index: 618962 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.9776. Min Act: -0.0001

Data Index: 1041128 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.8636. Min Act: -0.0001

Data Index: 1052800 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.7105. Min Act: -0.0001

Data Index: 21522 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.7797. Min Act: -0.0001

Data Index: 603905 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.9969. Min Act: -0.0001

Data Index: 978691 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.6453. Min Act: -0.0001

Data Index: 40911 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.7676. Min Act: -0.0001

Data Index: 1307468 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.4834. Min Act: -0.0001

Data Index: 533319 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.5905. Min Act: -0.0001

Data Index: 535535 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.5624. Min Act: -0.0001

Data Index: 550803 (C4 (Web Text))

Max Activating Token Index: 859

Text #17

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.3713. Min Act: -0.0001

Data Index: 1340215 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.3536. Min Act: -0.0001

Data Index: 542871 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 3.4673. Min Range: -3.4673

Max Act: 2.4610. Min Act: -0.0001

Data Index: 1177887 (C4 (Web Text))

Max Activating Token Index: 90