Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5946. Min Act: 0.0000

Data Index: 696581 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1768924 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5230. Min Act: -0.0000

Data Index: 141275 (The Pile)

Max Activating Token Index: 448

Text #3

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5158. Min Act: -0.0000

Data Index: 1951525 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5193. Min Act: -0.0000

Data Index: 271550 (The Pile)

Max Activating Token Index: 1007

Text #5

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5140. Min Act: -0.0000

Data Index: 1139034 (The Pile)

Max Activating Token Index: 311

Text #6

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5253. Min Act: -0.0000

Data Index: 291558 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5259. Min Act: -0.0001

Data Index: 1823813 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5198. Min Act: -0.0000

Data Index: 581189 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1858121 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4676. Min Act: -0.0000

Data Index: 149229 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4762. Min Act: -0.0000

Data Index: 1543628 (The Pile)

Max Activating Token Index: 510

Text #12

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4544. Min Act: -0.0000

Data Index: 593036 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1329853 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4668. Min Act: 0.0000

Data Index: 460515 (The Pile)

Max Activating Token Index: 141

Text #15

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4372. Min Act: -0.0000

Data Index: 1114209 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4461. Min Act: -0.0000

Data Index: 856657 (The Pile)

Max Activating Token Index: 830

Text #17

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1488147 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1219011 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 0.5946. Min Range: -0.5946

Max Act: 0.4273. Min Act: -0.0000

Data Index: 63608 (The Pile)

Max Activating Token Index: 264