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

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

Neuron 2607 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.9362. Min Act: -0.0000

Data Index: 636126 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.9185. Min Act: -0.0000

Data Index: 445030 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.9347. Min Act: -0.0000

Data Index: 911382 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1011007 (C4 (Web Text))

Max Activating Token Index: 365

Text #4

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1051282 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1162024 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8851. Min Act: -0.0000

Data Index: 954339 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8223. Min Act: -0.0000

Data Index: 479008 (C4 (Web Text))

Max Activating Token Index: 324

Text #8

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1179261 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8319. Min Act: -0.0000

Data Index: 87961 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8923. Min Act: -0.0000

Data Index: 20491 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8397. Min Act: -0.0000

Data Index: 916818 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8706. Min Act: -0.0000

Data Index: 152997 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8569. Min Act: -0.0000

Data Index: 862130 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1168925 (C4 (Web Text))

Max Activating Token Index: 651

Text #15

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8696. Min Act: -0.0000

Data Index: 725847 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7440. Min Act: -0.0000

Data Index: 760050 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1297342 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8302. Min Act: -0.0000

Data Index: 427089 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.9362. Min Range: -0.9362

Max Act: 0.8060. Min Act: -0.0001

Data Index: 330198 (C4 (Web Text))

Max Activating Token Index: 397