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

Dataset: The Pile

Neuron 1798 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: 1.2511. Min Range: -1.2511

Max Act: 1.1032. Min Act: -0.0000

Data Index: 801781 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0861. Min Act: -0.0000

Data Index: 892988 (The Pile)

Max Activating Token Index: 189

Text #2

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1977. Min Act: -0.0000

Data Index: 9423 (The Pile)

Max Activating Token Index: 913

Text #3

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.2511. Min Act: -0.0000

Data Index: 358195 (The Pile)

Max Activating Token Index: 341

Text #4

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0837. Min Act: -0.0000

Data Index: 303023 (The Pile)

Max Activating Token Index: 540

Text #5

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0112. Min Act: -0.0000

Data Index: 204494 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0651. Min Act: -0.0000

Data Index: 996819 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1223. Min Act: -0.0000

Data Index: 827608 (The Pile)

Max Activating Token Index: 227

Text #8

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9903. Min Act: -0.0000

Data Index: 760662 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1975673 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0835. Min Act: -0.0000

Data Index: 696545 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1687760 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.8986. Min Act: -0.0000

Data Index: 1453914 (The Pile)

Max Activating Token Index: 496

Text #13

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1854749 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1998982 (The Pile)

Max Activating Token Index: 281

Text #15

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9805. Min Act: -0.0000

Data Index: 5567 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1455963 (The Pile)

Max Activating Token Index: 230

Text #17

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9662. Min Act: -0.0000

Data Index: 302958 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1832490 (The Pile)

Max Activating Token Index: 117

Text #19

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1915749 (The Pile)

Max Activating Token Index: 791