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

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

Neuron 3672 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: 1.2241. Min Range: -1.2241

Max Act: 1.2241. Min Act: -0.0001

Data Index: 589875 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 1.2241. Min Range: -1.2241

Max Act: 1.0493. Min Act: -0.0001

Data Index: 583868 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 1.2241. Min Range: -1.2241

Max Act: 1.0200. Min Act: -0.0001

Data Index: 1319798 (C4 (Web Text))

Max Activating Token Index: 151

Text #3

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9799. Min Act: -0.0001

Data Index: 1301194 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.8445. Min Act: -0.0001

Data Index: 892864 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9316. Min Act: -0.0001

Data Index: 169458 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9904. Min Act: -0.0001

Data Index: 953268 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9567. Min Act: -0.0001

Data Index: 1324538 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9758. Min Act: -0.0001

Data Index: 355188 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9465. Min Act: -0.0001

Data Index: 658277 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9442. Min Act: -0.0001

Data Index: 679625 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9705. Min Act: -0.0001

Data Index: 1207414 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9380. Min Act: -0.0001

Data Index: 1195200 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.8827. Min Act: -0.0001

Data Index: 995537 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9084. Min Act: -0.0001

Data Index: 430534 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9289. Min Act: -0.0001

Data Index: 99584 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.8958. Min Act: -0.0001

Data Index: 645305 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.8596. Min Act: -0.0001

Data Index: 194407 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9126. Min Act: -0.0001

Data Index: 713303 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 1.2241. Min Range: -1.2241

Max Act: 0.9139. Min Act: -0.0001

Data Index: 703014 (C4 (Web Text))

Max Activating Token Index: 334