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

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

Neuron 3747 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.3029. Min Act: -0.0001

Data Index: 664280 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2840. Min Act: -0.0001

Data Index: 1059141 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2911. Min Act: -0.0001

Data Index: 715874 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2547. Min Act: -0.0001

Data Index: 1102291 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2681. Min Act: -0.0001

Data Index: 876256 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2477. Min Act: -0.0001

Data Index: 723940 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2490. Min Act: -0.0001

Data Index: 476777 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2333. Min Act: -0.0001

Data Index: 1024466 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2410. Min Act: -0.0001

Data Index: 215051 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2354. Min Act: -0.0001

Data Index: 704769 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2494. Min Act: -0.0001

Data Index: 477964 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2396. Min Act: -0.0001

Data Index: 117510 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2395. Min Act: -0.0001

Data Index: 1321058 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2476. Min Act: -0.0001

Data Index: 336360 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2455. Min Act: -0.0001

Data Index: 426898 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2347. Min Act: -0.0001

Data Index: 1254565 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2421. Min Act: -0.0001

Data Index: 1167777 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2328. Min Act: -0.0001

Data Index: 347973 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2320. Min Act: -0.0001

Data Index: 102034 (C4 (Web Text))

Max Activating Token Index: 468

Text #19

Max Range: 0.3029. Min Range: -0.3029

Max Act: 0.2240. Min Act: -0.0001

Data Index: 753166 (C4 (Web Text))

Max Activating Token Index: 430