Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 118 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.5186. Min Act: -0.0001

Data Index: 822101 (C4 (Web Text))

Max Activating Token Index: 326

Text #1

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4967. Min Act: -0.0001

Data Index: 1251255 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4976. Min Act: 0.0003

Data Index: 628127 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4946. Min Act: -0.0001

Data Index: 26493 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4866. Min Act: -0.0001

Data Index: 1394490 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1137124 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4876. Min Act: -0.0001

Data Index: 535621 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4460. Min Act: -0.0001

Data Index: 1063531 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4533. Min Act: -0.0001

Data Index: 632540 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4534. Min Act: -0.0001

Data Index: 1190986 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4630. Min Act: -0.0001

Data Index: 860506 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4407. Min Act: 0.0001

Data Index: 214361 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4689. Min Act: -0.0000

Data Index: 625412 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4396. Min Act: -0.0001

Data Index: 622403 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4280. Min Act: -0.0000

Data Index: 429439 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4022. Min Act: -0.0000

Data Index: 626674 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4319. Min Act: -0.0001

Data Index: 413138 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4292. Min Act: -0.0001

Data Index: 587436 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.4442. Min Act: -0.0001

Data Index: 812921 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.5186. Min Range: -0.5186

Max Act: 0.3952. Min Act: -0.0000

Data Index: 821868 (C4 (Web Text))

Max Activating Token Index: 875