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

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

Neuron 4083 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8865. Min Act: -0.0000

Data Index: 956611 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8023. Min Act: -0.0000

Data Index: 934621 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1235389 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8424. Min Act: -0.0000

Data Index: 413138 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7634. Min Act: -0.0000

Data Index: 684895 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1310352 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8768. Min Act: -0.0000

Data Index: 746697 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1359815 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8952. Min Act: -0.0000

Data Index: 881314 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1559541 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7309. Min Act: -0.0000

Data Index: 459827 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.8056. Min Act: -0.0000

Data Index: 209147 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7617. Min Act: -0.0000

Data Index: 425109 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7548. Min Act: -0.0000

Data Index: 521277 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7289. Min Act: -0.0000

Data Index: 205874 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1101934 (C4 (Web Text))

Max Activating Token Index: 265

Text #16

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7141. Min Act: -0.0000

Data Index: 934309 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7182. Min Act: -0.0000

Data Index: 895736 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7504. Min Act: -0.0000

Data Index: 285460 (C4 (Web Text))

Max Activating Token Index: 72

Text #19

Max Range: 0.8952. Min Range: -0.8952

Max Act: 0.7318. Min Act: -0.0000

Data Index: 226622 (C4 (Web Text))

Max Activating Token Index: 982