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

Dataset: The Pile

Neuron 1178 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: 1.9189. Min Range: -1.9189

Max Act: 1.8952. Min Act: -0.0000

Data Index: 645964 (The Pile)

Max Activating Token Index: 184

Text #1

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6690. Min Act: -0.0000

Data Index: 1742379 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6575. Min Act: -0.0000

Data Index: 1566477 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.9189. Min Act: -0.0000

Data Index: 758943 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1668884 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.6350. Min Act: -0.0000

Data Index: 1674850 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4290. Min Act: -0.0000

Data Index: 1142456 (The Pile)

Max Activating Token Index: 605

Text #7

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.5600. Min Act: -0.0000

Data Index: 985760 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3880. Min Act: -0.0000

Data Index: 763370 (The Pile)

Max Activating Token Index: 907

Text #9

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4450. Min Act: -0.0000

Data Index: 642454 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4755. Min Act: -0.0000

Data Index: 1247182 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4048. Min Act: -0.0000

Data Index: 182118 (The Pile)

Max Activating Token Index: 229

Text #12

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1441802 (The Pile)

Max Activating Token Index: 242

Text #13

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.3961. Min Act: -0.0000

Data Index: 719244 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4398. Min Act: -0.0000

Data Index: 560141 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4087. Min Act: -0.0000

Data Index: 25519 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4121. Min Act: -0.0000

Data Index: 699214 (The Pile)

Max Activating Token Index: 195

Text #17

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4265. Min Act: -0.0000

Data Index: 1414560 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.1965. Min Act: -0.0000

Data Index: 176150 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 1.9189. Min Range: -1.9189

Max Act: 1.4677. Min Act: -0.0000

Data Index: 414545 (The Pile)

Max Activating Token Index: 359