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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3905 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.7269. Min Act: -0.0001

Data Index: 259010 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.7305. Min Act: -0.0001

Data Index: 1320776 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6136. Min Act: -0.0001

Data Index: 391860 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1137794 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5902. Min Act: -0.0001

Data Index: 347315 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6468. Min Act: -0.0001

Data Index: 615905 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6280. Min Act: -0.0001

Data Index: 665355 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6464. Min Act: -0.0001

Data Index: 682832 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5827. Min Act: -0.0001

Data Index: 957446 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5958. Min Act: -0.0000

Data Index: 410540 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6387. Min Act: -0.0001

Data Index: 1120636 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6106. Min Act: -0.0001

Data Index: 290254 (C4 (Web Text))

Max Activating Token Index: 462

Text #12

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5899. Min Act: -0.0001

Data Index: 21178 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1008858 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5675. Min Act: -0.0001

Data Index: 1105245 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5740. Min Act: -0.0001

Data Index: 1097790 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6229. Min Act: -0.0001

Data Index: 937083 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6342. Min Act: -0.0001

Data Index: 711054 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.4802. Min Act: -0.0000

Data Index: 191484 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5862. Min Act: -0.0001

Data Index: 698202 (C4 (Web Text))

Max Activating Token Index: 984