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

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

Neuron 3407 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: 0.7205. Min Range: -0.7205

Max Act: 0.7000. Min Act: -0.0001

Data Index: 982915 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.7205. Min Act: -0.0001

Data Index: 468730 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6574. Min Act: -0.0001

Data Index: 63407 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6543. Min Act: -0.0001

Data Index: 646645 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6287. Min Act: -0.0001

Data Index: 1230556 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.6130. Min Act: -0.0000

Data Index: 808717 (C4 (Web Text))

Max Activating Token Index: 299

Text #6

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5932. Min Act: -0.0000

Data Index: 272087 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1252316 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5540. Min Act: -0.0001

Data Index: 1041650 (C4 (Web Text))

Max Activating Token Index: 1020

Text #9

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1097585 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5235. Min Act: -0.0001

Data Index: 621935 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5700. Min Act: -0.0001

Data Index: 612717 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5457. Min Act: -0.0001

Data Index: 1184772 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5465. Min Act: -0.0000

Data Index: 94610 (C4 (Web Text))

Max Activating Token Index: 1020

Text #14

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5208. Min Act: -0.0001

Data Index: 1254336 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5335. Min Act: -0.0001

Data Index: 595209 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5320. Min Act: -0.0000

Data Index: 729911 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5492. Min Act: -0.0000

Data Index: 899737 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.4977. Min Act: -0.0001

Data Index: 428463 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.7205. Min Range: -0.7205

Max Act: 0.5269. Min Act: -0.0001

Data Index: 1322315 (C4 (Web Text))

Max Activating Token Index: 96