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

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

Neuron 3719 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1330. Min Range: -2.1330

Max Act: 2.0442. Min Act: -0.0000

Data Index: 1221538 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 2.1330. Min Range: -2.1330

Max Act: 2.0249. Min Act: -0.0000

Data Index: 356077 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 2.1330. Min Range: -2.1330

Max Act: 2.0258. Min Act: -0.0000

Data Index: 1415940 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 2.1330. Min Range: -2.1330

Max Act: 2.1330. Min Act: -0.0000

Data Index: 92306 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.9982. Min Act: -0.0000

Data Index: 338548 (C4 (Web Text))

Max Activating Token Index: 820

Text #5

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.9312. Min Act: -0.0000

Data Index: 1441914 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 2.1330. Min Range: -2.1330

Max Act: 2.0269. Min Act: -0.0000

Data Index: 1401810 (Python Code)

Max Activating Token Index: 243

Text #7

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1420999 (Python Code)

Max Activating Token Index: 934

Text #8

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.8717. Min Act: -0.0000

Data Index: 1505342 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.7442. Min Act: -0.0000

Data Index: 4595 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.6408. Min Act: -0.0000

Data Index: 1395270 (Python Code)

Max Activating Token Index: 236

Text #11

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.5989. Min Act: -0.0000

Data Index: 1625685 (Python Code)

Max Activating Token Index: 817

Text #12

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.6628. Min Act: -0.0000

Data Index: 1402693 (Python Code)

Max Activating Token Index: 79

Text #13

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.4384. Min Act: -0.0000

Data Index: 1602298 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.4076. Min Act: -0.0000

Data Index: 1655620 (Python Code)

Max Activating Token Index: 19

Text #15

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.4532. Min Act: -0.0000

Data Index: 1498596 (Python Code)

Max Activating Token Index: 575

Text #16

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.5330. Min Act: -0.0000

Data Index: 1369348 (Python Code)

Max Activating Token Index: 689

Text #17

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.6100. Min Act: -0.0000

Data Index: 729855 (C4 (Web Text))

Max Activating Token Index: 921

Text #18

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.4273. Min Act: -0.0000

Data Index: 1296929 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 2.1330. Min Range: -2.1330

Max Act: 1.4207. Min Act: -0.0000

Data Index: 1465530 (Python Code)

Max Activating Token Index: 304