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

Dataset: The Pile

Neuron 1856 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: 0.4374. Min Range: -0.4374

Max Act: 0.4258. Min Act: -0.0000

Data Index: 1157623 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1575285 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.4244. Min Act: -0.0000

Data Index: 679294 (The Pile)

Max Activating Token Index: 34

Text #3

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3610. Min Act: -0.0000

Data Index: 1131183 (The Pile)

Max Activating Token Index: 564

Text #4

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3406. Min Act: -0.0000

Data Index: 188174 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1940178 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1788638 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3443. Min Act: -0.0000

Data Index: 1536547 (The Pile)

Max Activating Token Index: 225

Text #8

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3456. Min Act: -0.0000

Data Index: 700857 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3564. Min Act: -0.0000

Data Index: 1024363 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3302. Min Act: -0.0000

Data Index: 766374 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3315. Min Act: -0.0000

Data Index: 416088 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1879191 (The Pile)

Max Activating Token Index: 690

Text #13

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3040. Min Act: -0.0000

Data Index: 829302 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1814633 (The Pile)

Max Activating Token Index: 21

Text #15

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3119. Min Act: -0.0000

Data Index: 148974 (The Pile)

Max Activating Token Index: 70

Text #16

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3416. Min Act: -0.0000

Data Index: 1943986 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3302. Min Act: -0.0000

Data Index: 1703944 (The Pile)

Max Activating Token Index: 588

Text #18

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3184. Min Act: -0.0000

Data Index: 654183 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 0.4374. Min Range: -0.4374

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1756842 (The Pile)

Max Activating Token Index: 82