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

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

Neuron 5383 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2717. Min Range: -5.2717

Max Act: 5.2717. Min Act: -0.0000

Data Index: 1024073 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.9527. Min Act: -0.0000

Data Index: 671844 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.9302. Min Act: -0.0000

Data Index: 350502 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.8506. Min Act: -0.0000

Data Index: 123822 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.7539. Min Act: -0.0000

Data Index: 1150492 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.7302. Min Act: -0.0000

Data Index: 1028521 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.8246. Min Act: -0.0000

Data Index: 1103609 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.6118. Min Act: -0.0000

Data Index: 1298274 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.7855. Min Act: -0.0000

Data Index: 548299 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.5472. Min Act: -0.0000

Data Index: 1157261 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.5178. Min Act: -0.0000

Data Index: 613115 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.3039. Min Act: -0.0000

Data Index: 470606 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.4802. Min Act: -0.0000

Data Index: 609010 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.4259. Min Act: -0.0000

Data Index: 14321 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.3122. Min Act: -0.0000

Data Index: 1096531 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.2854. Min Act: -0.0000

Data Index: 1320541 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.4466. Min Act: -0.0000

Data Index: 779827 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.4653. Min Act: -0.0000

Data Index: 383622 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.4283. Min Act: -0.0000

Data Index: 813750 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 5.2717. Min Range: -5.2717

Max Act: 4.3993. Min Act: -0.0000

Data Index: 337631 (C4 (Web Text))

Max Activating Token Index: 654