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

Dataset: The Pile

Neuron 276 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.5292. Min Act: -0.0000

Data Index: 1645577 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1180148 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2760. Min Act: -0.0000

Data Index: 1781834 (The Pile)

Max Activating Token Index: 103

Text #3

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1830306 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2078. Min Act: -0.0000

Data Index: 248334 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.2616. Min Act: -0.0000

Data Index: 333819 (The Pile)

Max Activating Token Index: 60

Text #6

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1535845 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0936. Min Act: -0.0000

Data Index: 1766939 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1169. Min Act: -0.0000

Data Index: 748702 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1061. Min Act: -0.0000

Data Index: 1062130 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0628. Min Act: -0.0000

Data Index: 604039 (The Pile)

Max Activating Token Index: 630

Text #11

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1212. Min Act: -0.0000

Data Index: 126181 (The Pile)

Max Activating Token Index: 219

Text #12

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1523. Min Act: -0.0000

Data Index: 1701983 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1053. Min Act: -0.0000

Data Index: 1104616 (The Pile)

Max Activating Token Index: 107

Text #14

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1835184 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1218219 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0331. Min Act: -0.0000

Data Index: 1046264 (The Pile)

Max Activating Token Index: 348

Text #17

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0165. Min Act: -0.0000

Data Index: 1659139 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1071268 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.5292. Min Range: -1.5292

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1853758 (The Pile)

Max Activating Token Index: 975