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

Dataset: The Pile

Neuron 1512 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.3193. Min Range: -12.3193

Max Act: 12.3193. Min Act: -0.0000

Data Index: 1893943 (The Pile)

Max Activating Token Index: 786

Text #1

Max Range: 12.3193. Min Range: -12.3193

Max Act: 12.2450. Min Act: -0.0000

Data Index: 244438 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 12.3193. Min Range: -12.3193

Max Act: 12.1054. Min Act: -0.0000

Data Index: 153031 (The Pile)

Max Activating Token Index: 28

Text #3

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.7531. Min Act: -0.0000

Data Index: 431171 (The Pile)

Max Activating Token Index: 203

Text #4

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.4847. Min Act: -0.0000

Data Index: 246304 (The Pile)

Max Activating Token Index: 994

Text #5

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.7001. Min Act: -0.0000

Data Index: 1391129 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.8325. Min Act: -0.0000

Data Index: 1095746 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.7029. Min Act: -0.0000

Data Index: 1276588 (The Pile)

Max Activating Token Index: 188

Text #8

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.3232. Min Act: -0.0000

Data Index: 241454 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.7970. Min Act: -0.0000

Data Index: 1031519 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.7485. Min Act: -0.0000

Data Index: 1325888 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.1068. Min Act: -0.0000

Data Index: 306489 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.5142. Min Act: -0.0000

Data Index: 1581045 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.5474. Min Act: -0.0000

Data Index: 1090475 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.1537. Min Act: -0.0000

Data Index: 520137 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.5988. Min Act: -0.0000

Data Index: 598815 (The Pile)

Max Activating Token Index: 986

Text #16

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.4728. Min Act: -0.0000

Data Index: 1485796 (The Pile)

Max Activating Token Index: 807

Text #17

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.4093. Min Act: -0.0000

Data Index: 1872504 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.5236. Min Act: -0.0000

Data Index: 652236 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 12.3193. Min Range: -12.3193

Max Act: 11.4939. Min Act: -0.0000

Data Index: 1648804 (The Pile)

Max Activating Token Index: 487