Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 20 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0548. Min Act: -0.0004

Data Index: 877911 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0503. Min Act: -0.0004

Data Index: 1049733 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0471. Min Act: -0.0004

Data Index: 298291 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0522. Min Act: -0.0004

Data Index: 137146 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0491. Min Act: -0.0004

Data Index: 878512 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0471. Min Act: -0.0004

Data Index: 53696 (C4 (Web Text))

Max Activating Token Index: 831

Text #6

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0505. Min Act: -0.0004

Data Index: 505207 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0466. Min Act: -0.0004

Data Index: 1115187 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0486. Min Act: -0.0004

Data Index: 1222625 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0486. Min Act: -0.0004

Data Index: 729170 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0476. Min Act: -0.0004

Data Index: 662204 (C4 (Web Text))

Max Activating Token Index: 1004

Text #11

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0493. Min Act: -0.0004

Data Index: 989540 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0462. Min Act: -0.0004

Data Index: 1250300 (C4 (Web Text))

Max Activating Token Index: 118

Text #13

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0472. Min Act: -0.0004

Data Index: 1298496 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0478. Min Act: -0.0004

Data Index: 869159 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0448. Min Act: -0.0004

Data Index: 458456 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0451. Min Act: -0.0004

Data Index: 421772 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0470. Min Act: -0.0004

Data Index: 759022 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0450. Min Act: -0.0004

Data Index: 961281 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.0548. Min Range: -0.0548

Max Act: 0.0460. Min Act: -0.0004

Data Index: 91814 (C4 (Web Text))

Max Activating Token Index: 307