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

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

Neuron 2671 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: 1.0280. Min Range: -1.0280

Max Act: 1.0280. Min Act: -0.0002

Data Index: 1126680 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9895. Min Act: -0.0001

Data Index: 647075 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9255. Min Act: -0.0002

Data Index: 394844 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9227. Min Act: -0.0001

Data Index: 141114 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9953. Min Act: -0.0001

Data Index: 864356 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9041. Min Act: -0.0001

Data Index: 1262061 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9035. Min Act: -0.0002

Data Index: 752893 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9325. Min Act: -0.0002

Data Index: 1072121 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9043. Min Act: -0.0002

Data Index: 1132011 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8974. Min Act: -0.0002

Data Index: 817664 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9151. Min Act: -0.0001

Data Index: 1233841 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8882. Min Act: -0.0002

Data Index: 905988 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9162. Min Act: -0.0002

Data Index: 26351 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8819. Min Act: -0.0002

Data Index: 205080 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8866. Min Act: -0.0001

Data Index: 772453 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9058. Min Act: -0.0002

Data Index: 1007990 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8804. Min Act: -0.0002

Data Index: 377499 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8760. Min Act: -0.0002

Data Index: 160394 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8714. Min Act: -0.0002

Data Index: 972471 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.8750. Min Act: -0.0002

Data Index: 966276 (C4 (Web Text))

Max Activating Token Index: 1017