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

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

Neuron 1384 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3474. Min Act: -0.0000

Data Index: 1018942 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3352. Min Act: -0.0001

Data Index: 786765 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2973. Min Act: -0.0000

Data Index: 743617 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.3019. Min Act: -0.0000

Data Index: 840968 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2749. Min Act: -0.0001

Data Index: 1048212 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2867. Min Act: -0.0000

Data Index: 428199 (C4 (Web Text))

Max Activating Token Index: 689

Text #6

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2779. Min Act: -0.0001

Data Index: 677016 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2593. Min Act: -0.0000

Data Index: 494968 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1019228 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2592. Min Act: -0.0000

Data Index: 142359 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2685. Min Act: -0.0000

Data Index: 1247230 (C4 (Web Text))

Max Activating Token Index: 431

Text #11

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2668. Min Act: -0.0000

Data Index: 978304 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1302839 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2433. Min Act: -0.0000

Data Index: 814864 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2575. Min Act: -0.0000

Data Index: 1093708 (C4 (Web Text))

Max Activating Token Index: 756

Text #15

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2549. Min Act: -0.0001

Data Index: 581222 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2442. Min Act: -0.0000

Data Index: 533179 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2564. Min Act: -0.0000

Data Index: 293485 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2520. Min Act: -0.0001

Data Index: 925559 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.3474. Min Range: -0.3474

Max Act: 0.2529. Min Act: -0.0000

Data Index: 388141 (C4 (Web Text))

Max Activating Token Index: 683