Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 614 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.7252. Min Act: -0.0000

Data Index: 709418 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.6808. Min Act: -0.0000

Data Index: 1108056 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5411. Min Act: -0.0000

Data Index: 243256 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1102688 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4781. Min Act: -0.0000

Data Index: 618009 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4782. Min Act: -0.0000

Data Index: 444034 (C4 (Web Text))

Max Activating Token Index: 619

Text #6

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4918. Min Act: -0.0000

Data Index: 493818 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4673. Min Act: -0.0000

Data Index: 570953 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4433. Min Act: -0.0000

Data Index: 1349127 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4728. Min Act: -0.0000

Data Index: 946490 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1115567 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4569. Min Act: -0.0000

Data Index: 296847 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4342. Min Act: -0.0000

Data Index: 1084319 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.3999. Min Act: -0.0000

Data Index: 1111326 (C4 (Web Text))

Max Activating Token Index: 983

Text #14

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4148. Min Act: -0.0000

Data Index: 471632 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4548. Min Act: -0.0000

Data Index: 474877 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.3942. Min Act: -0.0000

Data Index: 993739 (C4 (Web Text))

Max Activating Token Index: 398

Text #17

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1257878 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1220293 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.7252. Min Range: -0.7252

Max Act: 0.4302. Min Act: -0.0000

Data Index: 903674 (C4 (Web Text))

Max Activating Token Index: 717