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

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

Neuron 5035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.8382. Min Act: -0.0000

Data Index: 876300 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.6467. Min Act: -0.0001

Data Index: 1006121 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.6044. Min Act: -0.0000

Data Index: 665606 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.6644. Min Act: -0.0000

Data Index: 1274053 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.6273. Min Act: -0.0000

Data Index: 581653 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.6445. Min Act: -0.0000

Data Index: 154228 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.5627. Min Act: -0.0000

Data Index: 936461 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.4449. Min Act: -0.0000

Data Index: 1090824 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.4385. Min Act: -0.0000

Data Index: 814881 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.4314. Min Act: -0.0000

Data Index: 469148 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3835. Min Act: -0.0000

Data Index: 538681 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3572. Min Act: -0.0000

Data Index: 958315 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3264. Min Act: -0.0000

Data Index: 362468 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3025. Min Act: -0.0000

Data Index: 695546 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3499. Min Act: -0.0000

Data Index: 720885 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.2947. Min Act: -0.0000

Data Index: 1079518 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3379. Min Act: -0.0000

Data Index: 776016 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3609. Min Act: -0.0000

Data Index: 110552 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.2595. Min Act: -0.0000

Data Index: 489384 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 1.8382. Min Range: -1.8382

Max Act: 1.3298. Min Act: -0.0000

Data Index: 1011637 (C4 (Web Text))

Max Activating Token Index: 8