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

Dataset: The Pile

Neuron 2802 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.6170. Min Act: -0.0000

Data Index: 327608 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1161114 (The Pile)

Max Activating Token Index: 405

Text #2

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4618. Min Act: -0.0000

Data Index: 929020 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4574. Min Act: -0.0000

Data Index: 998888 (The Pile)

Max Activating Token Index: 199

Text #4

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4261. Min Act: -0.0000

Data Index: 389672 (The Pile)

Max Activating Token Index: 207

Text #5

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4326. Min Act: -0.0000

Data Index: 417435 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4422. Min Act: -0.0000

Data Index: 106086 (The Pile)

Max Activating Token Index: 231

Text #7

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4574. Min Act: -0.0000

Data Index: 630721 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4434. Min Act: -0.0000

Data Index: 712770 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4242. Min Act: -0.0000

Data Index: 292133 (The Pile)

Max Activating Token Index: 713

Text #10

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4248. Min Act: -0.0000

Data Index: 664565 (The Pile)

Max Activating Token Index: 227

Text #11

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4394. Min Act: -0.0000

Data Index: 402077 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4462. Min Act: -0.0000

Data Index: 6790 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4130. Min Act: -0.0000

Data Index: 271422 (The Pile)

Max Activating Token Index: 565

Text #14

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4282. Min Act: -0.0000

Data Index: 686592 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1172315 (The Pile)

Max Activating Token Index: 560

Text #16

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4008. Min Act: -0.0000

Data Index: 1781761 (The Pile)

Max Activating Token Index: 453

Text #17

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1022840 (The Pile)

Max Activating Token Index: 310

Text #18

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4051. Min Act: -0.0000

Data Index: 738528 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1149780 (The Pile)

Max Activating Token Index: 831