Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1724 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0358. Min Act: -0.0003

Data Index: 781329 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0335. Min Act: -0.0003

Data Index: 241534 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0330. Min Act: -0.0003

Data Index: 431557 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0318. Min Act: -0.0003

Data Index: 451835 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0313. Min Act: -0.0003

Data Index: 763834 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0307. Min Act: -0.0003

Data Index: 483314 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0307. Min Act: -0.0003

Data Index: 63483 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0303. Min Act: -0.0002

Data Index: 656749 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0307. Min Act: -0.0003

Data Index: 530675 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0305. Min Act: -0.0003

Data Index: 552024 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0303. Min Act: -0.0003

Data Index: 149419 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0302. Min Act: -0.0003

Data Index: 854173 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1244186 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1052470 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0297. Min Act: -0.0003

Data Index: 424520 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0293. Min Act: -0.0003

Data Index: 556447 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0292. Min Act: -0.0003

Data Index: 93599 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0293. Min Act: -0.0003

Data Index: 964979 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1144045 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.0358. Min Range: -0.0358

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1192767 (C4 (Web Text))

Max Activating Token Index: 698