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

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

Neuron 195 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0600. Min Act: -0.0001

Data Index: 172122 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1055214 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0557. Min Act: -0.0001

Data Index: 1328056 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0505. Min Act: -0.0001

Data Index: 45782 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1399265 (Python Code)

Max Activating Token Index: 648

Text #5

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0534. Min Act: -0.0001

Data Index: 69684 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1586764 (Python Code)

Max Activating Token Index: 70

Text #7

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0501. Min Act: -0.0001

Data Index: 219130 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0496. Min Act: -0.0001

Data Index: 786559 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0491. Min Act: -0.0001

Data Index: 1208296 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0496. Min Act: -0.0001

Data Index: 152435 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0485. Min Act: -0.0001

Data Index: 135228 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0492. Min Act: -0.0001

Data Index: 498249 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0491. Min Act: -0.0001

Data Index: 72475 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0494. Min Act: -0.0001

Data Index: 506126 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0480. Min Act: -0.0001

Data Index: 462417 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0501. Min Act: -0.0001

Data Index: 421739 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0476. Min Act: -0.0001

Data Index: 1537857 (Python Code)

Max Activating Token Index: 458

Text #18

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0485. Min Act: -0.0001

Data Index: 964672 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.0600. Min Range: -0.0600

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1478357 (Python Code)

Max Activating Token Index: 5