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

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

Neuron 2623 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: 1.7248. Min Range: -1.7248

Max Act: 1.7248. Min Act: -0.0001

Data Index: 686035 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.4644. Min Act: -0.0001

Data Index: 761881 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.5963. Min Act: -0.0001

Data Index: 1182697 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3798. Min Act: -0.0001

Data Index: 1618111 (Python Code)

Max Activating Token Index: 967

Text #4

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2716. Min Act: -0.0001

Data Index: 1413591 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2335. Min Act: -0.0001

Data Index: 1328283 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.3001. Min Act: -0.0001

Data Index: 1028160 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2970. Min Act: -0.0001

Data Index: 1170049 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2455. Min Act: -0.0001

Data Index: 68651 (C4 (Web Text))

Max Activating Token Index: 311

Text #9

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2230. Min Act: -0.0001

Data Index: 976832 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.2658. Min Act: -0.0001

Data Index: 637665 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1218. Min Act: -0.0001

Data Index: 977254 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1291. Min Act: -0.0001

Data Index: 39319 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.0763. Min Act: -0.0001

Data Index: 1255892 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1802. Min Act: -0.0001

Data Index: 153823 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1499311 (Python Code)

Max Activating Token Index: 434

Text #16

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1345. Min Act: -0.0001

Data Index: 643888 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.0327. Min Act: -0.0001

Data Index: 256602 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.0684. Min Act: -0.0001

Data Index: 19477 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 1.7248. Min Range: -1.7248

Max Act: 1.1474. Min Act: -0.0001

Data Index: 526385 (C4 (Web Text))

Max Activating Token Index: 846