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

Dataset: The Pile

Neuron 338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.6901. Min Act: -0.0000

Data Index: 145320 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.7174. Min Act: -0.0000

Data Index: 1366298 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.7112. Min Act: -0.0000

Data Index: 90231 (The Pile)

Max Activating Token Index: 814

Text #3

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.1795. Min Act: -0.0000

Data Index: 1791186 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.4632. Min Act: -0.0000

Data Index: 1851337 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.4323. Min Act: -0.0000

Data Index: 488132 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.3777. Min Act: -0.0000

Data Index: 411082 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.4039. Min Act: -0.0000

Data Index: 1414938 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.2028. Min Act: -0.0000

Data Index: 106318 (The Pile)

Max Activating Token Index: 633

Text #9

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.2102. Min Act: -0.0000

Data Index: 438302 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.2196. Min Act: -0.0000

Data Index: 954526 (The Pile)

Max Activating Token Index: 30

Text #11

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.2888. Min Act: -0.0000

Data Index: 7039 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1379471 (The Pile)

Max Activating Token Index: 683

Text #13

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1317582 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0661. Min Act: -0.0000

Data Index: 1595624 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.1081. Min Act: -0.0000

Data Index: 177422 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0365. Min Act: -0.0000

Data Index: 371465 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0126. Min Act: -0.0000

Data Index: 203974 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0188. Min Act: -0.0000

Data Index: 1969094 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 1.7174. Min Range: -1.7174

Max Act: 1.0062. Min Act: -0.0000

Data Index: 588890 (The Pile)

Max Activating Token Index: 597