Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4044 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1719512 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1912064 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2876. Min Act: -0.0000

Data Index: 1298243 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2795. Min Act: -0.0000

Data Index: 1501400 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1621649 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2562. Min Act: -0.0000

Data Index: 966755 (The Pile)

Max Activating Token Index: 684

Text #6

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2525. Min Act: -0.0000

Data Index: 620199 (The Pile)

Max Activating Token Index: 433

Text #7

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2523. Min Act: -0.0000

Data Index: 1269810 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1508751 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2476. Min Act: -0.0000

Data Index: 1638464 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2223. Min Act: -0.0000

Data Index: 1737562 (The Pile)

Max Activating Token Index: 197

Text #11

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2326. Min Act: -0.0000

Data Index: 1973346 (The Pile)

Max Activating Token Index: 615

Text #12

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2173. Min Act: -0.0000

Data Index: 593576 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2399. Min Act: -0.0000

Data Index: 250840 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2159. Min Act: -0.0000

Data Index: 214810 (The Pile)

Max Activating Token Index: 802

Text #15

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1862550 (The Pile)

Max Activating Token Index: 85

Text #16

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2169. Min Act: -0.0000

Data Index: 523096 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2183. Min Act: -0.0000

Data Index: 157063 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1414151 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.3739. Min Range: -0.3739

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1214994 (The Pile)

Max Activating Token Index: 766