Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3853 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1268954 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.7601. Min Act: -0.0000

Data Index: 676301 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6995. Min Act: -0.0000

Data Index: 86177 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.6192. Min Act: -0.0000

Data Index: 1932907 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5341. Min Act: -0.0000

Data Index: 1639959 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5333. Min Act: -0.0000

Data Index: 1185346 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1739008 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.5305. Min Act: -0.0000

Data Index: 132888 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4564. Min Act: -0.0000

Data Index: 1218361 (The Pile)

Max Activating Token Index: 785

Text #9

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4208. Min Act: -0.0000

Data Index: 687772 (The Pile)

Max Activating Token Index: 503

Text #10

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1478607 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4085. Min Act: -0.0000

Data Index: 577355 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1155102 (The Pile)

Max Activating Token Index: 609

Text #13

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.3726. Min Act: -0.0000

Data Index: 651015 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1285081 (The Pile)

Max Activating Token Index: 412

Text #15

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.3880. Min Act: -0.0000

Data Index: 1008744 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1657219 (The Pile)

Max Activating Token Index: 297

Text #17

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.3469. Min Act: -0.0000

Data Index: 402423 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.3938. Min Act: -0.0000

Data Index: 599803 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.9129. Min Range: -0.9129

Max Act: 0.4369. Min Act: -0.0000

Data Index: 464276 (The Pile)

Max Activating Token Index: 393