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

Dataset: The Pile

Neuron 2425 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3190. Min Act: -0.0001

Data Index: 1082588 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3353. Min Act: -0.0001

Data Index: 120588 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3536. Min Act: -0.0000

Data Index: 1218506 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3346. Min Act: -0.0000

Data Index: 1533206 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3396. Min Act: -0.0001

Data Index: 126645 (The Pile)

Max Activating Token Index: 189

Text #5

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3305. Min Act: -0.0001

Data Index: 1199929 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1197547 (The Pile)

Max Activating Token Index: 621

Text #7

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3041. Min Act: -0.0000

Data Index: 1383984 (The Pile)

Max Activating Token Index: 691

Text #8

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3021. Min Act: -0.0000

Data Index: 1132644 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3126. Min Act: -0.0000

Data Index: 164852 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3274. Min Act: -0.0000

Data Index: 200852 (The Pile)

Max Activating Token Index: 938

Text #11

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3045. Min Act: -0.0000

Data Index: 329252 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3051. Min Act: -0.0001

Data Index: 651980 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2888. Min Act: -0.0001

Data Index: 975098 (The Pile)

Max Activating Token Index: 336

Text #14

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2811. Min Act: -0.0001

Data Index: 509564 (The Pile)

Max Activating Token Index: 982

Text #15

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2973. Min Act: -0.0000

Data Index: 1562278 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.3205. Min Act: -0.0000

Data Index: 633448 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2970. Min Act: -0.0000

Data Index: 787577 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2933. Min Act: -0.0001

Data Index: 10341 (The Pile)

Max Activating Token Index: 564

Text #19

Max Range: 0.3536. Min Range: -0.3536

Max Act: 0.2959. Min Act: -0.0001

Data Index: 151467 (The Pile)

Max Activating Token Index: 688