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

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

Neuron 2109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1163. Min Act: -0.0001

Data Index: 145791 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1137. Min Act: -0.0001

Data Index: 334803 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1255763 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1099967 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0966. Min Act: -0.0001

Data Index: 611566 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1209602 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0982. Min Act: -0.0001

Data Index: 26739 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0910. Min Act: -0.0001

Data Index: 87528 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0846. Min Act: -0.0001

Data Index: 1051564 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0879. Min Act: -0.0001

Data Index: 818187 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0843. Min Act: -0.0001

Data Index: 723451 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0860. Min Act: -0.0001

Data Index: 551456 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0899. Min Act: -0.0001

Data Index: 1218592 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1043300 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0791. Min Act: -0.0001

Data Index: 790712 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0769. Min Act: -0.0001

Data Index: 343747 (C4 (Web Text))

Max Activating Token Index: 270

Text #16

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0760. Min Act: -0.0001

Data Index: 1074021 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0776. Min Act: -0.0001

Data Index: 846230 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1106835 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 0.1163. Min Range: -0.1163

Max Act: 0.0727. Min Act: -0.0001

Data Index: 389959 (C4 (Web Text))

Max Activating Token Index: 887