Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1562 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.7972. Min Act: -0.0000

Data Index: 951210 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.7452. Min Act: -0.0000

Data Index: 1236737 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6623. Min Act: -0.0000

Data Index: 215773 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6830. Min Act: -0.0000

Data Index: 161224 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6348. Min Act: -0.0000

Data Index: 568466 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6905. Min Act: -0.0000

Data Index: 1250466 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6466. Min Act: -0.0000

Data Index: 1290597 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6604. Min Act: -0.0000

Data Index: 79819 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6163. Min Act: -0.0000

Data Index: 612939 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1073057 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1110264 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5850. Min Act: -0.0000

Data Index: 966525 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5774. Min Act: -0.0000

Data Index: 1449111 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1001233 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.6142. Min Act: 0.0001

Data Index: 341881 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5875. Min Act: -0.0000

Data Index: 354545 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5879. Min Act: 0.0000

Data Index: 1338652 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5903. Min Act: -0.0000

Data Index: 402783 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5613. Min Act: -0.0000

Data Index: 1357482 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.7972. Min Range: -0.7972

Max Act: 0.5529. Min Act: -0.0000

Data Index: 824382 (C4 (Web Text))

Max Activating Token Index: 12