Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2640 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1071099 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2942. Min Act: -0.0001

Data Index: 342490 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2801. Min Act: -0.0000

Data Index: 1334630 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2333. Min Act: -0.0001

Data Index: 886592 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1040595 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2408. Min Act: -0.0001

Data Index: 971173 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2212. Min Act: -0.0001

Data Index: 106425 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.2167. Min Act: -0.0000

Data Index: 527664 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1919. Min Act: -0.0001

Data Index: 577684 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1958. Min Act: -0.0001

Data Index: 173940 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1803. Min Act: -0.0001

Data Index: 1112890 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1732. Min Act: -0.0001

Data Index: 1211624 (C4 (Web Text))

Max Activating Token Index: 473

Text #12

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1207089 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1256153 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1271929 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1693. Min Act: -0.0001

Data Index: 568484 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1574. Min Act: -0.0001

Data Index: 1332719 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1728. Min Act: -0.0001

Data Index: 989791 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1054189 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.3246. Min Range: -0.3246

Max Act: 0.1612. Min Act: -0.0001

Data Index: 210889 (C4 (Web Text))

Max Activating Token Index: 322