Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2660 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3191. Min Act: -0.0000

Data Index: 62291 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3187. Min Act: -0.0000

Data Index: 1805843 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3101. Min Act: -0.0000

Data Index: 1648521 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1168916 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1006736 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2920. Min Act: -0.0000

Data Index: 767776 (The Pile)

Max Activating Token Index: 1011

Text #6

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2584. Min Act: 0.0000

Data Index: 106187 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2372. Min Act: 0.0000

Data Index: 971208 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2514. Min Act: -0.0000

Data Index: 121025 (The Pile)

Max Activating Token Index: 878

Text #9

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1306644 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2483. Min Act: -0.0000

Data Index: 452233 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1128325 (The Pile)

Max Activating Token Index: 643

Text #12

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1673094 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2200. Min Act: -0.0000

Data Index: 218987 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2407. Min Act: -0.0000

Data Index: 962758 (The Pile)

Max Activating Token Index: 630

Text #15

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2408. Min Act: 0.0000

Data Index: 1754908 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2415. Min Act: 0.0000

Data Index: 1323835 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2354. Min Act: 0.0000

Data Index: 905984 (The Pile)

Max Activating Token Index: 953

Text #18

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1904713 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2197. Min Act: 0.0000

Data Index: 1307634 (The Pile)

Max Activating Token Index: 1018