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

Dataset: The Pile

Neuron 2828 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: 0.9369. Min Range: -0.9369

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1436100 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.8094. Min Act: -0.0000

Data Index: 612438 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.7409. Min Act: -0.0000

Data Index: 680251 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1769701 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1085155 (The Pile)

Max Activating Token Index: 72

Text #5

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5877. Min Act: -0.0000

Data Index: 1180340 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1829315 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4978. Min Act: -0.0000

Data Index: 862877 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4936. Min Act: -0.0000

Data Index: 673721 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4932. Min Act: -0.0000

Data Index: 1827659 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1833048 (The Pile)

Max Activating Token Index: 805

Text #11

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1528665 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4820. Min Act: -0.0000

Data Index: 586278 (The Pile)

Max Activating Token Index: 608

Text #13

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4646. Min Act: -0.0000

Data Index: 324707 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4609. Min Act: -0.0000

Data Index: 915835 (The Pile)

Max Activating Token Index: 337

Text #15

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1158859 (The Pile)

Max Activating Token Index: 591

Text #16

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4943. Min Act: -0.0000

Data Index: 122236 (The Pile)

Max Activating Token Index: 468

Text #17

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4603. Min Act: -0.0000

Data Index: 1211174 (The Pile)

Max Activating Token Index: 291

Text #18

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4722. Min Act: -0.0000

Data Index: 1571309 (The Pile)

Max Activating Token Index: 514

Text #19

Max Range: 0.9369. Min Range: -0.9369

Max Act: 0.4700. Min Act: -0.0000

Data Index: 169467 (The Pile)

Max Activating Token Index: 256