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

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

Neuron 2083 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.5096. Min Act: -0.0001

Data Index: 886652 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.5252. Min Act: -0.0000

Data Index: 288787 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.6970. Min Act: -0.0001

Data Index: 498683 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.2610. Min Act: -0.0001

Data Index: 606830 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.3835. Min Act: -0.0001

Data Index: 1238790 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.2769. Min Act: -0.0000

Data Index: 854291 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.0454. Min Act: -0.0001

Data Index: 1238984 (C4 (Web Text))

Max Activating Token Index: 924

Text #7

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.7857. Min Act: -0.0001

Data Index: 1296604 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.6711. Min Act: -0.0001

Data Index: 509714 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.7564. Min Act: -0.0000

Data Index: 563750 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.6839. Min Act: -0.0001

Data Index: 128545 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 3.6970. Min Range: -3.6970

Max Act: 3.0466. Min Act: -0.0001

Data Index: 590092 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.6554. Min Act: -0.0001

Data Index: 668658 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.6129. Min Act: -0.0001

Data Index: 1258087 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.7099. Min Act: -0.0001

Data Index: 1273006 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.4354. Min Act: -0.0001

Data Index: 828905 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.3928. Min Act: -0.0001

Data Index: 633811 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.2553. Min Act: -0.0001

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.4241. Min Act: -0.0001

Data Index: 1302095 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 3.6970. Min Range: -3.6970

Max Act: 2.3063. Min Act: -0.0000

Data Index: 207499 (C4 (Web Text))

Max Activating Token Index: 739