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

Dataset: The Pile

Neuron 1983 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3474. Min Act: -0.0000

Data Index: 488551 (The Pile)

Max Activating Token Index: 916

Text #1

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1142218 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1740968 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1384417 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1132265 (The Pile)

Max Activating Token Index: 750

Text #5

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3261. Min Act: -0.0000

Data Index: 780081 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2907. Min Act: -0.0000

Data Index: 1557470 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2902. Min Act: -0.0000

Data Index: 1416793 (The Pile)

Max Activating Token Index: 468

Text #8

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1604385 (The Pile)

Max Activating Token Index: 443

Text #9

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2702. Min Act: -0.0000

Data Index: 255429 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1995795 (The Pile)

Max Activating Token Index: 387

Text #11

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2138. Min Act: -0.0000

Data Index: 1425905 (The Pile)

Max Activating Token Index: 138

Text #12

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2452. Min Act: -0.0000

Data Index: 148902 (The Pile)

Max Activating Token Index: 555

Text #13

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1186565 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2312. Min Act: -0.0000

Data Index: 613163 (The Pile)

Max Activating Token Index: 815

Text #15

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2247. Min Act: -0.0000

Data Index: 408064 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1824214 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1845057 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1013707 (The Pile)

Max Activating Token Index: 874

Text #19

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2253. Min Act: -0.0000

Data Index: 123083 (The Pile)

Max Activating Token Index: 566