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

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

Neuron 1135 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: 2.4902. Min Range: -2.4902

Max Act: 2.4902. Min Act: -0.0000

Data Index: 665061 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8279. Min Act: -0.0000

Data Index: 364043 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8970. Min Act: -0.0000

Data Index: 172770 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8933. Min Act: -0.0000

Data Index: 584191 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8655. Min Act: -0.0000

Data Index: 222958 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8431. Min Act: -0.0000

Data Index: 390219 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.8084. Min Act: -0.0000

Data Index: 155318 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.7986. Min Act: -0.0000

Data Index: 967528 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.7775. Min Act: -0.0000

Data Index: 1322712 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.7200. Min Act: -0.0000

Data Index: 1058782 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.7076. Min Act: -0.0000

Data Index: 155031 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.7000. Min Act: -0.0000

Data Index: 1326347 (C4 (Web Text))

Max Activating Token Index: 967

Text #12

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6111. Min Act: -0.0000

Data Index: 291189 (C4 (Web Text))

Max Activating Token Index: 535

Text #13

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6956. Min Act: -0.0000

Data Index: 671874 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.5894. Min Act: -0.0000

Data Index: 281163 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6726. Min Act: -0.0000

Data Index: 935044 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6784. Min Act: -0.0000

Data Index: 554823 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6566. Min Act: -0.0000

Data Index: 905629 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6466. Min Act: -0.0000

Data Index: 836448 (C4 (Web Text))

Max Activating Token Index: 97

Text #19

Max Range: 2.4902. Min Range: -2.4902

Max Act: 1.6458. Min Act: -0.0000

Data Index: 1015175 (C4 (Web Text))

Max Activating Token Index: 432