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

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

Neuron 3918 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0000

Data Index: 108958 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0519. Min Act: -0.0000

Data Index: 823924 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1107323 (C4 (Web Text))

Max Activating Token Index: 1003

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0509. Min Act: -0.0000

Data Index: 445432 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0508. Min Act: -0.0000

Data Index: 359303 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0489. Min Act: -0.0000

Data Index: 997035 (C4 (Web Text))

Max Activating Token Index: 858

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0457. Min Act: -0.0000

Data Index: 14574 (C4 (Web Text))

Max Activating Token Index: 968

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1189938 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1216630 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0480. Min Act: -0.0000

Data Index: 105796 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0476. Min Act: -0.0000

Data Index: 804398 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0474. Min Act: -0.0000

Data Index: 275343 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0455. Min Act: -0.0000

Data Index: 367816 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0469. Min Act: -0.0000

Data Index: 983638 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0452. Min Act: -0.0000

Data Index: 664407 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0448. Min Act: -0.0000

Data Index: 564993 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0442. Min Act: -0.0000

Data Index: 199412 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0443. Min Act: -0.0000

Data Index: 996995 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0464. Min Act: -0.0000

Data Index: 872345 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0439. Min Act: -0.0000

Data Index: 1220025 (C4 (Web Text))

Max Activating Token Index: 202