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

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

Neuron 2302 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.9943. Min Act: -0.0000

Data Index: 174649 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7654. Min Act: -0.0000

Data Index: 764344 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8323. Min Act: -0.0001

Data Index: 275518 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8253. Min Act: -0.0001

Data Index: 500353 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7511. Min Act: -0.0000

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7671. Min Act: -0.0000

Data Index: 847312 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.8012. Min Act: -0.0000

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7794. Min Act: -0.0001

Data Index: 1036681 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7771. Min Act: -0.0000

Data Index: 463720 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1641365 (Python Code)

Max Activating Token Index: 430

Text #10

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7817. Min Act: -0.0001

Data Index: 873123 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7319. Min Act: -0.0000

Data Index: 155836 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1355522 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7512. Min Act: -0.0001

Data Index: 97891 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7570. Min Act: -0.0001

Data Index: 904163 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7026. Min Act: -0.0000

Data Index: 291811 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7442. Min Act: -0.0000

Data Index: 436648 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.6940. Min Act: -0.0001

Data Index: 958332 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7132. Min Act: -0.0000

Data Index: 30632 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.9943. Min Range: -0.9943

Max Act: 0.7542. Min Act: -0.0000

Data Index: 749862 (C4 (Web Text))

Max Activating Token Index: 883