Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 137 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.5486. Min Act: -0.0001

Data Index: 198338 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.4291. Min Act: -0.0001

Data Index: 1164587 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1272417 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.1384. Min Act: -0.0001

Data Index: 960129 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.8351. Min Act: -0.0001

Data Index: 539706 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.9370. Min Act: -0.0001

Data Index: 1139384 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.5486. Min Range: -1.5486

Max Act: 1.0037. Min Act: -0.0001

Data Index: 703873 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.5967. Min Act: -0.0001

Data Index: 24964 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.6493. Min Act: -0.0001

Data Index: 310426 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.8831. Min Act: -0.0001

Data Index: 144665 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.8928. Min Act: -0.0001

Data Index: 295411 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.8348. Min Act: -0.0001

Data Index: 132363 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7510. Min Act: -0.0001

Data Index: 1298003 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7474. Min Act: -0.0001

Data Index: 836837 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1250850 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7703. Min Act: -0.0001

Data Index: 126531 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.6380. Min Act: -0.0001

Data Index: 600651 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7230. Min Act: -0.0001

Data Index: 740183 (C4 (Web Text))

Max Activating Token Index: 982

Text #18

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7299. Min Act: -0.0001

Data Index: 727835 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.5486. Min Range: -1.5486

Max Act: 0.7721. Min Act: -0.0001

Data Index: 369627 (C4 (Web Text))

Max Activating Token Index: 631