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

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

Neuron 3198 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.4380. Min Act: -0.0001

Data Index: 905875 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.4300. Min Act: -0.0001

Data Index: 1022582 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.4293. Min Act: -0.0001

Data Index: 38675 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3902. Min Act: -0.0001

Data Index: 1076786 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3945. Min Act: -0.0001

Data Index: 1291028 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3928. Min Act: -0.0001

Data Index: 4406 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3732. Min Act: -0.0001

Data Index: 395579 (C4 (Web Text))

Max Activating Token Index: 346

Text #7

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3968. Min Act: -0.0001

Data Index: 657217 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3720. Min Act: -0.0001

Data Index: 294949 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1617559 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3539. Min Act: -0.0001

Data Index: 357716 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3523. Min Act: -0.0001

Data Index: 243143 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1455674 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3680. Min Act: -0.0001

Data Index: 663475 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1458419 (Python Code)

Max Activating Token Index: 974

Text #15

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3176. Min Act: -0.0001

Data Index: 541544 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3886. Min Act: -0.0001

Data Index: 892321 (C4 (Web Text))

Max Activating Token Index: 352

Text #17

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3331. Min Act: -0.0001

Data Index: 1249336 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3503. Min Act: -0.0001

Data Index: 270492 (C4 (Web Text))

Max Activating Token Index: 666

Text #19

Max Range: 0.4380. Min Range: -0.4380

Max Act: 0.3489. Min Act: -0.0001

Data Index: 1085705 (C4 (Web Text))

Max Activating Token Index: 469