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

Dataset: The Pile

Neuron 2300 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: 0.3159. Min Range: -0.3159

Max Act: 0.3159. Min Act: -0.0000

Data Index: 1659471 (The Pile)

Max Activating Token Index: 824

Text #1

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2833. Min Act: -0.0000

Data Index: 378659 (The Pile)

Max Activating Token Index: 253

Text #2

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2686. Min Act: -0.0000

Data Index: 986879 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2439. Min Act: -0.0000

Data Index: 178111 (The Pile)

Max Activating Token Index: 489

Text #4

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2482. Min Act: -0.0000

Data Index: 702432 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2466. Min Act: -0.0000

Data Index: 673368 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2243. Min Act: -0.0000

Data Index: 186383 (The Pile)

Max Activating Token Index: 524

Text #7

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2314. Min Act: -0.0000

Data Index: 985540 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1217151 (The Pile)

Max Activating Token Index: 858

Text #9

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2119. Min Act: -0.0000

Data Index: 11833 (The Pile)

Max Activating Token Index: 707

Text #10

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2255. Min Act: -0.0000

Data Index: 901154 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2225. Min Act: -0.0000

Data Index: 646317 (The Pile)

Max Activating Token Index: 545

Text #12

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1412756 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1565203 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2070. Min Act: -0.0000

Data Index: 14735 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1157225 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1073192 (The Pile)

Max Activating Token Index: 175

Text #17

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2142. Min Act: -0.0000

Data Index: 344917 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.1970. Min Act: -0.0000

Data Index: 369482 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.3159. Min Range: -0.3159

Max Act: 0.2024. Min Act: -0.0000

Data Index: 373278 (The Pile)

Max Activating Token Index: 341