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

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

Neuron 3124 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3711. Min Act: -0.0001

Data Index: 525176 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3639. Min Act: -0.0001

Data Index: 262705 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1030766 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3358. Min Act: -0.0001

Data Index: 488244 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3337. Min Act: -0.0001

Data Index: 588262 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3343. Min Act: -0.0001

Data Index: 466633 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3303. Min Act: -0.0001

Data Index: 709785 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3160. Min Act: -0.0001

Data Index: 871255 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3233. Min Act: -0.0001

Data Index: 424344 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3128. Min Act: -0.0001

Data Index: 313500 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3018. Min Act: -0.0001

Data Index: 953975 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3101. Min Act: -0.0001

Data Index: 27350 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3136. Min Act: -0.0001

Data Index: 190970 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1093197 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.3018. Min Act: -0.0001

Data Index: 994107 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2772. Min Act: -0.0001

Data Index: 1046497 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2667. Min Act: -0.0001

Data Index: 632934 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2703. Min Act: -0.0001

Data Index: 351412 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2653. Min Act: -0.0001

Data Index: 152870 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 0.3711. Min Range: -0.3711

Max Act: 0.2755. Min Act: -0.0001

Data Index: 528747 (C4 (Web Text))

Max Activating Token Index: 315