Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5573 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3687. Min Act: -0.0000

Data Index: 311842 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3475. Min Act: -0.0000

Data Index: 623760 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3224. Min Act: -0.0000

Data Index: 425787 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.3152. Min Act: -0.0000

Data Index: 730267 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2879. Min Act: -0.0000

Data Index: 1111838 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2937. Min Act: -0.0000

Data Index: 1232042 (C4 (Web Text))

Max Activating Token Index: 285

Text #6

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2894. Min Act: -0.0000

Data Index: 889592 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2730. Min Act: -0.0000

Data Index: 30455 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1233745 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2615. Min Act: -0.0000

Data Index: 410327 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2673. Min Act: -0.0000

Data Index: 368708 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2568. Min Act: -0.0000

Data Index: 45601 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1013770 (C4 (Web Text))

Max Activating Token Index: 440

Text #13

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2443. Min Act: -0.0000

Data Index: 798767 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2455. Min Act: -0.0000

Data Index: 341825 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2572. Min Act: -0.0000

Data Index: 1161252 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2516. Min Act: -0.0000

Data Index: 786639 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2434. Min Act: -0.0000

Data Index: 1185170 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2461. Min Act: -0.0000

Data Index: 908452 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.3687. Min Range: -0.3687

Max Act: 0.2383. Min Act: -0.0000

Data Index: 898050 (C4 (Web Text))

Max Activating Token Index: 626