Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 232 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0374. Min Range: -2.0374

Max Act: 2.0374. Min Act: -0.0000

Data Index: 1571366 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.6961. Min Act: -0.0000

Data Index: 1054620 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.6540. Min Act: -0.0000

Data Index: 953372 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.6491. Min Act: -0.0000

Data Index: 604660 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.5324. Min Act: -0.0000

Data Index: 1325959 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.5776. Min Act: -0.0000

Data Index: 1152337 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4743. Min Act: -0.0000

Data Index: 429235 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4989. Min Act: -0.0000

Data Index: 160432 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.5114. Min Act: -0.0000

Data Index: 1285057 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4405. Min Act: -0.0000

Data Index: 1083365 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4974. Min Act: -0.0000

Data Index: 455250 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4760. Min Act: -0.0000

Data Index: 1168466 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4741. Min Act: -0.0000

Data Index: 1324291 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4662. Min Act: -0.0000

Data Index: 407678 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.3915. Min Act: -0.0000

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.2711. Min Act: -0.0000

Data Index: 748346 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4301. Min Act: -0.0000

Data Index: 408138 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4321. Min Act: -0.0000

Data Index: 365406 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1286297 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 2.0374. Min Range: -2.0374

Max Act: 1.3765. Min Act: -0.0000

Data Index: 260519 (C4 (Web Text))

Max Activating Token Index: 312