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

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

Neuron 887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.6150. Min Act: -0.0000

Data Index: 1311781 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.3053. Min Act: -0.0000

Data Index: 1062963 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.2994. Min Act: -0.0000

Data Index: 208375 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.2543. Min Act: -0.0000

Data Index: 996327 (C4 (Web Text))

Max Activating Token Index: 917

Text #4

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.2341. Min Act: -0.0000

Data Index: 1092706 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.1040. Min Act: -0.0000

Data Index: 818626 (C4 (Web Text))

Max Activating Token Index: 684

Text #6

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.9672. Min Act: -0.0000

Data Index: 1294764 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.0430. Min Act: -0.0000

Data Index: 1357261 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.0193. Min Act: -0.0000

Data Index: 318218 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.9447. Min Act: -0.0000

Data Index: 234225 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.0037. Min Act: -0.0000

Data Index: 932233 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 2.6150. Min Range: -2.6150

Max Act: 2.0522. Min Act: -0.0000

Data Index: 899254 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.9488. Min Act: -0.0000

Data Index: 129593 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1291581 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.8704. Min Act: -0.0000

Data Index: 1010426 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.9895. Min Act: -0.0000

Data Index: 540894 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.7810. Min Act: -0.0000

Data Index: 138483 (C4 (Web Text))

Max Activating Token Index: 124

Text #17

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.7654. Min Act: -0.0000

Data Index: 455520 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.8027. Min Act: -0.0000

Data Index: 522028 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 2.6150. Min Range: -2.6150

Max Act: 1.8319. Min Act: -0.0000

Data Index: 429477 (C4 (Web Text))

Max Activating Token Index: 709