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

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

Neuron 3273 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7655. Min Act: -0.0002

Data Index: 18111 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7573. Min Act: -0.0001

Data Index: 879534 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7532. Min Act: -0.0002

Data Index: 497656 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6710. Min Act: -0.0001

Data Index: 543968 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6990. Min Act: -0.0002

Data Index: 292662 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7060. Min Act: -0.0002

Data Index: 524639 (C4 (Web Text))

Max Activating Token Index: 888

Text #6

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7312. Min Act: -0.0002

Data Index: 472565 (C4 (Web Text))

Max Activating Token Index: 3

Text #7

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6882. Min Act: -0.0001

Data Index: 438008 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7080. Min Act: -0.0002

Data Index: 869625 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7117. Min Act: -0.0002

Data Index: 1118148 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6472. Min Act: -0.0001

Data Index: 1195518 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6957. Min Act: -0.0001

Data Index: 872851 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6882. Min Act: -0.0001

Data Index: 903301 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6626. Min Act: -0.0001

Data Index: 628176 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7274. Min Act: -0.0001

Data Index: 488364 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6621. Min Act: -0.0002

Data Index: 1146078 (C4 (Web Text))

Max Activating Token Index: 319

Text #16

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6788. Min Act: -0.0002

Data Index: 380141 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.7150. Min Act: -0.0001

Data Index: 219044 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6929. Min Act: -0.0002

Data Index: 276248 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.7655. Min Range: -0.7655

Max Act: 0.6629. Min Act: -0.0001

Data Index: 200208 (C4 (Web Text))

Max Activating Token Index: 810