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

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

Neuron 1548 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0697. Min Range: -1.0697

Max Act: 1.0697. Min Act: -0.0000

Data Index: 1019745 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.8876. Min Act: -0.0000

Data Index: 828698 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.8148. Min Act: -0.0000

Data Index: 125327 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.8058. Min Act: -0.0000

Data Index: 1447002 (Python Code)

Max Activating Token Index: 220

Text #4

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1335465 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.8121. Min Act: -0.0000

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7665. Min Act: -0.0000

Data Index: 641151 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1047636 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7548. Min Act: -0.0000

Data Index: 949717 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7584. Min Act: 0.0000

Data Index: 165392 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.8031. Min Act: -0.0000

Data Index: 60573 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7960. Min Act: -0.0000

Data Index: 719692 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7463. Min Act: 0.0001

Data Index: 352122 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1426663 (Python Code)

Max Activating Token Index: 965

Text #15

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7310. Min Act: -0.0000

Data Index: 367539 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7529. Min Act: -0.0000

Data Index: 717322 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7803. Min Act: 0.0000

Data Index: 278186 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7623. Min Act: -0.0000

Data Index: 118374 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 1.0697. Min Range: -1.0697

Max Act: 0.7251. Min Act: 0.0000

Data Index: 513193 (C4 (Web Text))

Max Activating Token Index: 141