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

Dataset: The Pile

Neuron 2467 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: 0.7942. Min Range: -0.7942

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1308086 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1831206 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1043047 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1799464 (The Pile)

Max Activating Token Index: 32

Text #4

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6787. Min Act: -0.0000

Data Index: 456400 (The Pile)

Max Activating Token Index: 444

Text #5

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6872. Min Act: -0.0000

Data Index: 468876 (The Pile)

Max Activating Token Index: 926

Text #6

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7185. Min Act: -0.0000

Data Index: 1221556 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6818. Min Act: -0.0000

Data Index: 631709 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1363652 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6516. Min Act: -0.0000

Data Index: 276120 (The Pile)

Max Activating Token Index: 621

Text #10

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6622. Min Act: -0.0000

Data Index: 936258 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6803. Min Act: -0.0000

Data Index: 1126184 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1986042 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1974227 (The Pile)

Max Activating Token Index: 1011

Text #14

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1828505 (The Pile)

Max Activating Token Index: 71

Text #15

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1702881 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6276. Min Act: -0.0000

Data Index: 202723 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6384. Min Act: -0.0000

Data Index: 603872 (The Pile)

Max Activating Token Index: 151

Text #18

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6331. Min Act: -0.0000

Data Index: 821989 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6281. Min Act: -0.0000

Data Index: 417228 (The Pile)

Max Activating Token Index: 146