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

Dataset: The Pile

Neuron 518 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: 1.2205. Min Range: -1.2205

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1734714 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0537. Min Act: -0.0000

Data Index: 1298225 (The Pile)

Max Activating Token Index: 910

Text #2

Max Range: 1.2205. Min Range: -1.2205

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1612794 (The Pile)

Max Activating Token Index: 513

Text #3

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1061560 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9001. Min Act: -0.0000

Data Index: 134495 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1736761 (The Pile)

Max Activating Token Index: 229

Text #6

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1362941 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.9078. Min Act: -0.0000

Data Index: 331232 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8981. Min Act: -0.0000

Data Index: 418475 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8409. Min Act: 0.0000

Data Index: 1929764 (The Pile)

Max Activating Token Index: 516

Text #10

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8801. Min Act: -0.0000

Data Index: 217767 (The Pile)

Max Activating Token Index: 248

Text #11

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8021. Min Act: -0.0000

Data Index: 787362 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8559. Min Act: -0.0000

Data Index: 584778 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1618633 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7369. Min Act: 0.0000

Data Index: 420989 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1914974 (The Pile)

Max Activating Token Index: 758

Text #16

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7907. Min Act: -0.0000

Data Index: 542031 (The Pile)

Max Activating Token Index: 295

Text #17

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.8148. Min Act: -0.0000

Data Index: 1513642 (The Pile)

Max Activating Token Index: 269

Text #18

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1215130 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.2205. Min Range: -1.2205

Max Act: 0.7662. Min Act: -0.0000

Data Index: 364962 (The Pile)

Max Activating Token Index: 962