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

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

Neuron 905 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0784. Min Range: -1.0784

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1087516 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.9436. Min Act: -0.0000

Data Index: 1311776 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.8294. Min Act: -0.0000

Data Index: 115044 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.8205. Min Act: -0.0000

Data Index: 564612 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.8526. Min Act: -0.0000

Data Index: 499029 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1024489 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7777. Min Act: -0.0000

Data Index: 471111 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.8140. Min Act: -0.0000

Data Index: 268168 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1325938 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7037. Min Act: -0.0000

Data Index: 209421 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7077. Min Act: 0.0000

Data Index: 1083739 (C4 (Web Text))

Max Activating Token Index: 556

Text #11

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7475. Min Act: -0.0000

Data Index: 192595 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7468. Min Act: -0.0000

Data Index: 15122 (C4 (Web Text))

Max Activating Token Index: 482

Text #13

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7386. Min Act: -0.0000

Data Index: 545199 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7398. Min Act: -0.0000

Data Index: 260033 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7363. Min Act: -0.0000

Data Index: 1033170 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.6832. Min Act: -0.0000

Data Index: 1119243 (C4 (Web Text))

Max Activating Token Index: 534

Text #17

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7251. Min Act: -0.0000

Data Index: 848738 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.6732. Min Act: 0.0000

Data Index: 39307 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.0784. Min Range: -1.0784

Max Act: 0.7590. Min Act: 0.0000

Data Index: 829027 (C4 (Web Text))

Max Activating Token Index: 189