Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1328 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2540. Min Act: -0.0001

Data Index: 1641616 (Python Code)

Max Activating Token Index: 99

Text #1

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2641. Min Act: -0.0001

Data Index: 1603157 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2591. Min Act: -0.0001

Data Index: 1628110 (Python Code)

Max Activating Token Index: 365

Text #3

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2623. Min Act: -0.0000

Data Index: 1579523 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2338. Min Act: -0.0001

Data Index: 1360939 (Python Code)

Max Activating Token Index: 410

Text #5

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1397589 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2244. Min Act: -0.0001

Data Index: 1471150 (Python Code)

Max Activating Token Index: 551

Text #7

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2266. Min Act: -0.0001

Data Index: 1413594 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2210. Min Act: -0.0001

Data Index: 1400603 (Python Code)

Max Activating Token Index: 236

Text #9

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2539. Min Act: 0.0001

Data Index: 1373360 (Python Code)

Max Activating Token Index: 1013

Text #10

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1549259 (Python Code)

Max Activating Token Index: 537

Text #11

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2158. Min Act: -0.0001

Data Index: 1610260 (Python Code)

Max Activating Token Index: 690

Text #12

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2153. Min Act: -0.0001

Data Index: 1541559 (Python Code)

Max Activating Token Index: 456

Text #13

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2185. Min Act: 0.0001

Data Index: 1654974 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1592180 (Python Code)

Max Activating Token Index: 337

Text #15

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1520855 (Python Code)

Max Activating Token Index: 513

Text #16

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1648435 (Python Code)

Max Activating Token Index: 621

Text #17

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1301141 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.2163. Min Act: -0.0001

Data Index: 1640527 (Python Code)

Max Activating Token Index: 730

Text #19

Max Range: 0.2641. Min Range: -0.2641

Max Act: 0.1970. Min Act: -0.0000

Data Index: 1648497 (Python Code)

Max Activating Token Index: 857