Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.9351. Min Act: -0.0000

Data Index: 787247 (The Pile)

Max Activating Token Index: 102

Text #1

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1151572 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7941. Min Act: -0.0000

Data Index: 484354 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8680. Min Act: -0.0000

Data Index: 954094 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1618622 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8027. Min Act: -0.0000

Data Index: 218735 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7929. Min Act: -0.0000

Data Index: 748764 (The Pile)

Max Activating Token Index: 142

Text #7

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1255186 (The Pile)

Max Activating Token Index: 532

Text #8

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1001923 (The Pile)

Max Activating Token Index: 391

Text #9

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7865. Min Act: -0.0000

Data Index: 883668 (The Pile)

Max Activating Token Index: 97

Text #10

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1894703 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7908. Min Act: -0.0000

Data Index: 706189 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1228025 (The Pile)

Max Activating Token Index: 526

Text #13

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1767383 (The Pile)

Max Activating Token Index: 369

Text #14

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7528. Min Act: -0.0000

Data Index: 182219 (The Pile)

Max Activating Token Index: 872

Text #15

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7524. Min Act: -0.0000

Data Index: 1988651 (The Pile)

Max Activating Token Index: 241

Text #16

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7521. Min Act: -0.0000

Data Index: 410556 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1357649 (The Pile)

Max Activating Token Index: 664

Text #18

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7051. Min Act: -0.0000

Data Index: 1092149 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.9351. Min Range: -0.9351

Max Act: 0.7285. Min Act: -0.0000

Data Index: 608460 (The Pile)

Max Activating Token Index: 148