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

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

Neuron 852 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.7292. Min Act: -0.0001

Data Index: 812293 (C4 (Web Text))

Max Activating Token Index: 450

Text #1

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4300. Min Act: -0.0001

Data Index: 760871 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.5889. Min Act: -0.0001

Data Index: 584396 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4423. Min Act: -0.0001

Data Index: 1349157 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4190. Min Act: -0.0001

Data Index: 1253447 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.2585. Min Act: -0.0001

Data Index: 216774 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 3.7292. Min Range: -3.7292

Max Act: 2.9708. Min Act: -0.0001

Data Index: 166202 (C4 (Web Text))

Max Activating Token Index: 756

Text #7

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.5444. Min Act: -0.0001

Data Index: 425223 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.6608. Min Act: -0.0001

Data Index: 119164 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.5241. Min Act: -0.0001

Data Index: 1143096 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.0328. Min Act: -0.0001

Data Index: 1106231 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4484. Min Act: -0.0001

Data Index: 62605 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.2798. Min Act: -0.0001

Data Index: 354477 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.4080. Min Act: -0.0001

Data Index: 1139828 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3915. Min Act: -0.0001

Data Index: 175809 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.2621. Min Act: -0.0001

Data Index: 1259179 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 3.7292. Min Range: -3.7292

Max Act: 2.9906. Min Act: -0.0001

Data Index: 546094 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.2536. Min Act: -0.0001

Data Index: 504259 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 3.7292. Min Range: -3.7292

Max Act: 3.3894. Min Act: -0.0001

Data Index: 247167 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 3.7292. Min Range: -3.7292

Max Act: 2.9293. Min Act: -0.0001

Data Index: 581027 (C4 (Web Text))

Max Activating Token Index: 934