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

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

Neuron 3248 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: 0.5244. Min Range: -0.5244

Max Act: 0.5244. Min Act: -0.0000

Data Index: 954226 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.5024. Min Act: -0.0000

Data Index: 597355 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4100. Min Act: -0.0001

Data Index: 437117 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4597. Min Act: -0.0001

Data Index: 117470 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4010. Min Act: -0.0001

Data Index: 273361 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3923. Min Act: -0.0000

Data Index: 1094391 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3865. Min Act: -0.0001

Data Index: 517053 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3993. Min Act: -0.0000

Data Index: 579525 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1244744 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3560. Min Act: -0.0001

Data Index: 407998 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1178826 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1238366 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1266026 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3941. Min Act: -0.0001

Data Index: 56181 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3526. Min Act: -0.0000

Data Index: 187554 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3372. Min Act: -0.0001

Data Index: 254581 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1212983 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3688. Min Act: -0.0000

Data Index: 228947 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1200705 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 0.5244. Min Range: -0.5244

Max Act: 0.3550. Min Act: -0.0001

Data Index: 1185817 (C4 (Web Text))

Max Activating Token Index: 124