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

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

Neuron 866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1616039 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1605596 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1367777 (Python Code)

Max Activating Token Index: 427

Text #3

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.5592. Min Act: -0.0000

Data Index: 1558586 (Python Code)

Max Activating Token Index: 757

Text #4

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1384726 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1580021 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1471523 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1577066 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1627420 (Python Code)

Max Activating Token Index: 127

Text #9

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3678. Min Act: -0.0000

Data Index: 1517592 (Python Code)

Max Activating Token Index: 117

Text #10

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3579. Min Act: -0.0000

Data Index: 1364115 (Python Code)

Max Activating Token Index: 473

Text #11

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3115. Min Act: -0.0000

Data Index: 652332 (C4 (Web Text))

Max Activating Token Index: 184

Text #12

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1585513 (Python Code)

Max Activating Token Index: 614

Text #13

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2734. Min Act: -0.0000

Data Index: 1561280 (Python Code)

Max Activating Token Index: 632

Text #14

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1544010 (Python Code)

Max Activating Token Index: 537

Text #15

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1374114 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2708. Min Act: -0.0000

Data Index: 629944 (C4 (Web Text))

Max Activating Token Index: 490

Text #17

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1377712 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2591. Min Act: -0.0000

Data Index: 352394 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.9007. Min Range: -0.9007

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1467769 (Python Code)

Max Activating Token Index: 888