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

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

Neuron 587 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.2366. Min Act: -0.0001

Data Index: 502640 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.2399. Min Act: -0.0001

Data Index: 696008 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1938. Min Act: -0.0001

Data Index: 460344 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0875. Min Act: -0.0001

Data Index: 1091546 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1887. Min Act: -0.0001

Data Index: 690755 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1456. Min Act: -0.0001

Data Index: 1609720 (Python Code)

Max Activating Token Index: 7

Text #6

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0255. Min Act: -0.0001

Data Index: 1357595 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1132407 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0189. Min Act: -0.0001

Data Index: 452399 (C4 (Web Text))

Max Activating Token Index: 970

Text #9

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1105. Min Act: -0.0001

Data Index: 1298611 (C4 (Web Text))

Max Activating Token Index: 411

Text #10

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0144. Min Act: -0.0001

Data Index: 841547 (C4 (Web Text))

Max Activating Token Index: 675

Text #11

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.1164. Min Act: -0.0001

Data Index: 242631 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9830. Min Act: -0.0001

Data Index: 102998 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0812. Min Act: -0.0001

Data Index: 773654 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0105. Min Act: -0.0001

Data Index: 140136 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9873. Min Act: -0.0001

Data Index: 1216914 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0201. Min Act: -0.0001

Data Index: 162715 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9883. Min Act: -0.0001

Data Index: 1303580 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 1.2399. Min Range: -1.2399

Max Act: 0.9679. Min Act: -0.0001

Data Index: 996614 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.2399. Min Range: -1.2399

Max Act: 1.0042. Min Act: -0.0001

Data Index: 1254261 (C4 (Web Text))

Max Activating Token Index: 33