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

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

Neuron 5057 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.7489. Min Act: -0.0000

Data Index: 649031 (C4 (Web Text))

Max Activating Token Index: 109

Text #1

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.7176. Min Act: -0.0000

Data Index: 292099 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1013338 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1336686 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6298. Min Act: -0.0000

Data Index: 901405 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6164. Min Act: -0.0000

Data Index: 696677 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6126. Min Act: -0.0000

Data Index: 56440 (C4 (Web Text))

Max Activating Token Index: 169

Text #7

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5955. Min Act: -0.0000

Data Index: 501941 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5774. Min Act: -0.0000

Data Index: 426353 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.6226. Min Act: -0.0000

Data Index: 947575 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5889. Min Act: -0.0000

Data Index: 887316 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5995. Min Act: -0.0000

Data Index: 1257715 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5915. Min Act: -0.0000

Data Index: 109920 (C4 (Web Text))

Max Activating Token Index: 328

Text #13

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5533. Min Act: -0.0000

Data Index: 985191 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5613. Min Act: -0.0000

Data Index: 441008 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5398. Min Act: -0.0000

Data Index: 436504 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5475. Min Act: -0.0000

Data Index: 505521 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5716. Min Act: -0.0000

Data Index: 383702 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5714. Min Act: -0.0000

Data Index: 1101652 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.7489. Min Range: -0.7489

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1067219 (C4 (Web Text))

Max Activating Token Index: 973