Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1186 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0005

Data Index: 883211 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0469. Min Act: -0.0006

Data Index: 663887 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0470. Min Act: -0.0006

Data Index: 266035 (C4 (Web Text))

Max Activating Token Index: 180

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0470. Min Act: -0.0006

Data Index: 341266 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0450. Min Act: -0.0006

Data Index: 857222 (C4 (Web Text))

Max Activating Token Index: 374

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0449. Min Act: -0.0006

Data Index: 859206 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0444. Min Act: -0.0006

Data Index: 772983 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0450. Min Act: -0.0006

Data Index: 896459 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0459. Min Act: -0.0006

Data Index: 1403929 (Python Code)

Max Activating Token Index: 352

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0440. Min Act: -0.0006

Data Index: 107717 (C4 (Web Text))

Max Activating Token Index: 533

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1022246 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0442. Min Act: -0.0006

Data Index: 1100638 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0432. Min Act: -0.0005

Data Index: 1343404 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1566230 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0429. Min Act: -0.0005

Data Index: 2702 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0404. Min Act: -0.0006

Data Index: 1112713 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0418. Min Act: -0.0006

Data Index: 1207082 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0425. Min Act: -0.0005

Data Index: 318360 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0432. Min Act: -0.0006

Data Index: 508760 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0420. Min Act: -0.0005

Data Index: 1168471 (C4 (Web Text))

Max Activating Token Index: 593