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

Dataset: The Pile

Neuron 4764 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.8341. Min Act: -0.0000

Data Index: 248274 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.7429. Min Act: -0.0000

Data Index: 290334 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6594. Min Act: -0.0000

Data Index: 1070775 (The Pile)

Max Activating Token Index: 157

Text #3

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.6341. Min Act: -0.0000

Data Index: 733621 (The Pile)

Max Activating Token Index: 770

Text #4

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1180923 (The Pile)

Max Activating Token Index: 218

Text #5

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5570. Min Act: -0.0000

Data Index: 1566498 (The Pile)

Max Activating Token Index: 80

Text #6

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5576. Min Act: -0.0000

Data Index: 129692 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1918280 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4153. Min Act: -0.0000

Data Index: 1871242 (The Pile)

Max Activating Token Index: 146

Text #9

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4993. Min Act: -0.0000

Data Index: 577124 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1322219 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4395. Min Act: -0.0000

Data Index: 68961 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4890. Min Act: -0.0000

Data Index: 1128042 (The Pile)

Max Activating Token Index: 134

Text #13

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.4947. Min Act: -0.0000

Data Index: 1428189 (The Pile)

Max Activating Token Index: 384

Text #14

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3910. Min Act: -0.0000

Data Index: 554020 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3181. Min Act: -0.0000

Data Index: 27544 (The Pile)

Max Activating Token Index: 1011

Text #16

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3064. Min Act: -0.0000

Data Index: 1113442 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.2800. Min Act: -0.0000

Data Index: 1972606 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1806819 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 1.8341. Min Range: -1.8341

Max Act: 1.3423. Min Act: -0.0000

Data Index: 1654471 (The Pile)

Max Activating Token Index: 194