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

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

Neuron 2724 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2792. Min Act: -0.0001

Data Index: 1478224 (Python Code)

Max Activating Token Index: 138

Text #1

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2706. Min Act: -0.0001

Data Index: 1379704 (Python Code)

Max Activating Token Index: 148

Text #2

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2735. Min Act: -0.0001

Data Index: 213368 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2530. Min Act: -0.0001

Data Index: 924738 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1635740 (Python Code)

Max Activating Token Index: 144

Text #5

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2426. Min Act: -0.0001

Data Index: 595859 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2668. Min Act: -0.0001

Data Index: 1085889 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1044486 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2081. Min Act: -0.0001

Data Index: 441896 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2454. Min Act: -0.0001

Data Index: 1622756 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2323. Min Act: -0.0001

Data Index: 427009 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2476. Min Act: -0.0001

Data Index: 1445009 (Python Code)

Max Activating Token Index: 942

Text #12

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2409. Min Act: -0.0001

Data Index: 685301 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2380. Min Act: -0.0001

Data Index: 693134 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2420. Min Act: -0.0001

Data Index: 418420 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2280. Min Act: -0.0001

Data Index: 510505 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2366. Min Act: -0.0001

Data Index: 1650051 (Python Code)

Max Activating Token Index: 247

Text #17

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2278. Min Act: -0.0001

Data Index: 409957 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2345. Min Act: -0.0001

Data Index: 366764 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.2792. Min Range: -0.2792

Max Act: 0.2506. Min Act: -0.0001

Data Index: 492680 (C4 (Web Text))

Max Activating Token Index: 152