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

Dataset: The Pile

Neuron 2671 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: 1.6169. Min Range: -1.6169

Max Act: 1.6169. Min Act: -0.0000

Data Index: 179018 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4005. Min Act: -0.0000

Data Index: 286529 (The Pile)

Max Activating Token Index: 308

Text #2

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1752903 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3927. Min Act: -0.0000

Data Index: 453516 (The Pile)

Max Activating Token Index: 413

Text #4

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.4094. Min Act: -0.0000

Data Index: 787577 (The Pile)

Max Activating Token Index: 888

Text #5

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3345. Min Act: -0.0000

Data Index: 173339 (The Pile)

Max Activating Token Index: 269

Text #6

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3954. Min Act: -0.0000

Data Index: 916524 (The Pile)

Max Activating Token Index: 310

Text #7

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3288. Min Act: -0.0000

Data Index: 569391 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1716072 (The Pile)

Max Activating Token Index: 702

Text #9

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2797. Min Act: -0.0000

Data Index: 262560 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2344. Min Act: -0.0000

Data Index: 1212596 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1250413 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3036. Min Act: -0.0000

Data Index: 711030 (The Pile)

Max Activating Token Index: 189

Text #13

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2565. Min Act: -0.0000

Data Index: 683242 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1125229 (The Pile)

Max Activating Token Index: 91

Text #15

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.1549. Min Act: -0.0000

Data Index: 1285741 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.3060. Min Act: -0.0000

Data Index: 983385 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.1671. Min Act: -0.0000

Data Index: 1516103 (The Pile)

Max Activating Token Index: 399

Text #18

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.1683. Min Act: -0.0000

Data Index: 364236 (The Pile)

Max Activating Token Index: 617

Text #19

Max Range: 1.6169. Min Range: -1.6169

Max Act: 1.2341. Min Act: -0.0000

Data Index: 1100194 (The Pile)

Max Activating Token Index: 253