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

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

Neuron 761 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: 0.0565. Min Range: -0.0565

Max Act: 0.0565. Min Act: -0.0006

Data Index: 25327 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0493. Min Act: -0.0006

Data Index: 248024 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0469. Min Act: -0.0006

Data Index: 793165 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0470. Min Act: -0.0006

Data Index: 402084 (C4 (Web Text))

Max Activating Token Index: 43

Text #4

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0475. Min Act: -0.0006

Data Index: 78094 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0444. Min Act: -0.0006

Data Index: 665637 (C4 (Web Text))

Max Activating Token Index: 181

Text #6

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0466. Min Act: -0.0006

Data Index: 615584 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0457. Min Act: -0.0006

Data Index: 811125 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0442. Min Act: -0.0006

Data Index: 149800 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0423. Min Act: -0.0006

Data Index: 686341 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0463. Min Act: -0.0006

Data Index: 606024 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0445. Min Act: -0.0006

Data Index: 1275397 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0443. Min Act: -0.0006

Data Index: 985278 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0432. Min Act: -0.0006

Data Index: 383233 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0439. Min Act: -0.0006

Data Index: 849985 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0454. Min Act: -0.0006

Data Index: 3044 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0433. Min Act: -0.0006

Data Index: 323829 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0432. Min Act: -0.0006

Data Index: 224536 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0421. Min Act: -0.0006

Data Index: 596143 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 0.0565. Min Range: -0.0565

Max Act: 0.0429. Min Act: -0.0006

Data Index: 162729 (C4 (Web Text))

Max Activating Token Index: 164