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

Dataset: The Pile

Neuron 909 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.5970. Min Act: -0.0000

Data Index: 377109 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.3574. Min Act: -0.0000

Data Index: 887084 (The Pile)

Max Activating Token Index: 645

Text #2

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.3646. Min Act: -0.0000

Data Index: 790073 (The Pile)

Max Activating Token Index: 209

Text #3

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1348822 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.2324. Min Act: -0.0000

Data Index: 1678138 (The Pile)

Max Activating Token Index: 425

Text #5

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1383. Min Act: -0.0000

Data Index: 143044 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1130849 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1554. Min Act: -0.0000

Data Index: 827700 (The Pile)

Max Activating Token Index: 832

Text #8

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1579. Min Act: -0.0000

Data Index: 1799912 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1952027 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1156. Min Act: -0.0000

Data Index: 32716 (The Pile)

Max Activating Token Index: 588

Text #11

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0477. Min Act: -0.0000

Data Index: 35773 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1697. Min Act: -0.0000

Data Index: 197279 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1038502 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0922. Min Act: -0.0000

Data Index: 1912273 (The Pile)

Max Activating Token Index: 881

Text #15

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.1025. Min Act: -0.0000

Data Index: 317212 (The Pile)

Max Activating Token Index: 759

Text #16

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1149896 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1399632 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0523. Min Act: -0.0000

Data Index: 399690 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 1.5970. Min Range: -1.5970

Max Act: 1.0266. Min Act: -0.0000

Data Index: 775938 (The Pile)

Max Activating Token Index: 114