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

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

Neuron 2458 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.3066. Min Act: -0.0000

Data Index: 1285850 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.6366. Min Act: -0.0000

Data Index: 902934 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.2612. Min Act: -0.0000

Data Index: 1126982 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.2999. Min Act: -0.0000

Data Index: 1359983 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.4702. Min Act: -0.0000

Data Index: 1429449 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.3339. Min Act: -0.0000

Data Index: 1578974 (Python Code)

Max Activating Token Index: 785

Text #6

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.3505. Min Act: -0.0000

Data Index: 1619508 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.2170. Min Act: -0.0000

Data Index: 1374943 (Python Code)

Max Activating Token Index: 958

Text #8

Max Range: 2.6366. Min Range: -2.6366

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1523070 (Python Code)

Max Activating Token Index: 963

Text #9

Max Range: 2.6366. Min Range: -2.6366

Max Act: 1.8553. Min Act: -0.0000

Data Index: 1648297 (Python Code)

Max Activating Token Index: 202

Text #10

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.0452. Min Act: -0.0000

Data Index: 1397827 (Python Code)

Max Activating Token Index: 148

Text #11

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.0540. Min Act: -0.0000

Data Index: 1525765 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.0545. Min Act: -0.0000

Data Index: 1397232 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.0099. Min Act: -0.0000

Data Index: 1642701 (Python Code)

Max Activating Token Index: 428

Text #14

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.0203. Min Act: -0.0000

Data Index: 1500141 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 2.6366. Min Range: -2.6366

Max Act: 1.9665. Min Act: -0.0000

Data Index: 1645077 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 2.6366. Min Range: -2.6366

Max Act: 1.9043. Min Act: -0.0000

Data Index: 1387603 (Python Code)

Max Activating Token Index: 311

Text #17

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.1700. Min Act: -0.0000

Data Index: 1498346 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.2204. Min Act: -0.0000

Data Index: 1402348 (Python Code)

Max Activating Token Index: 944

Text #19

Max Range: 2.6366. Min Range: -2.6366

Max Act: 2.1964. Min Act: -0.0000

Data Index: 1446727 (Python Code)

Max Activating Token Index: 910