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

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

Neuron 372 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0363. Min Act: -0.0004

Data Index: 19383 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0354. Min Act: -0.0004

Data Index: 734040 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0355. Min Act: -0.0004

Data Index: 641789 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0338. Min Act: -0.0004

Data Index: 514439 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0331. Min Act: -0.0004

Data Index: 751432 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0334. Min Act: -0.0004

Data Index: 814864 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0330. Min Act: -0.0004

Data Index: 1351533 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0335. Min Act: -0.0004

Data Index: 824833 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0321. Min Act: -0.0004

Data Index: 331769 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0311. Min Act: -0.0004

Data Index: 895139 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0311. Min Act: -0.0004

Data Index: 557330 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0315. Min Act: -0.0004

Data Index: 573413 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0320. Min Act: -0.0004

Data Index: 619545 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0316. Min Act: -0.0004

Data Index: 678100 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0307. Min Act: -0.0004

Data Index: 949155 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0303. Min Act: -0.0004

Data Index: 502406 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0303. Min Act: -0.0004

Data Index: 772913 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0325. Min Act: -0.0004

Data Index: 1272258 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0312. Min Act: -0.0004

Data Index: 575268 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.0363. Min Range: -0.0363

Max Act: 0.0297. Min Act: -0.0004

Data Index: 1016221 (C4 (Web Text))

Max Activating Token Index: 231