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

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

Neuron 2167 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.5389. Min Act: -0.0000

Data Index: 604897 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.3678. Min Act: -0.0000

Data Index: 699443 (C4 (Web Text))

Max Activating Token Index: 379

Text #2

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.6553. Min Act: -0.0001

Data Index: 233240 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.0370. Min Act: -0.0001

Data Index: 526980 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.8452. Min Act: -0.0000

Data Index: 721110 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.9310. Min Act: -0.0001

Data Index: 1045861 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.0800. Min Act: -0.0001

Data Index: 287095 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.7550. Min Act: -0.0000

Data Index: 457489 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 4.6553. Min Range: -4.6553

Max Act: 4.0536. Min Act: -0.0000

Data Index: 60989 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.6966. Min Act: -0.0001

Data Index: 937066 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.4702. Min Act: -0.0001

Data Index: 85756 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.7819. Min Act: -0.0001

Data Index: 871024 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.6757. Min Act: -0.0001

Data Index: 719416 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.5976. Min Act: -0.0000

Data Index: 146956 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.2885. Min Act: -0.0000

Data Index: 913598 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.4225. Min Act: -0.0000

Data Index: 153320 (C4 (Web Text))

Max Activating Token Index: 13

Text #16

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.5491. Min Act: -0.0001

Data Index: 1337808 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.4237. Min Act: -0.0001

Data Index: 1286521 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.5164. Min Act: -0.0000

Data Index: 663614 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 4.6553. Min Range: -4.6553

Max Act: 3.3793. Min Act: -0.0001

Data Index: 1303897 (C4 (Web Text))

Max Activating Token Index: 915