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

Dataset: The Pile

Neuron 683 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: 0.7406. Min Range: -0.7406

Max Act: 0.7369. Min Act: -0.0000

Data Index: 317914 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6726. Min Act: -0.0000

Data Index: 1027906 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7406. Min Act: -0.0000

Data Index: 273143 (The Pile)

Max Activating Token Index: 297

Text #3

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1873553 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1943146 (The Pile)

Max Activating Token Index: 582

Text #5

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5885. Min Act: -0.0000

Data Index: 965098 (The Pile)

Max Activating Token Index: 397

Text #6

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1682939 (The Pile)

Max Activating Token Index: 96

Text #7

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1768503 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6108. Min Act: -0.0000

Data Index: 194858 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1720707 (The Pile)

Max Activating Token Index: 74

Text #10

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5816. Min Act: 0.0000

Data Index: 1241964 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6262. Min Act: -0.0000

Data Index: 687955 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5872. Min Act: -0.0000

Data Index: 278027 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6380. Min Act: -0.0000

Data Index: 503376 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1917625 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6524. Min Act: -0.0000

Data Index: 682325 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5843. Min Act: -0.0000

Data Index: 1681664 (The Pile)

Max Activating Token Index: 235

Text #17

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5879. Min Act: -0.0000

Data Index: 304233 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1615797 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6461. Min Act: -0.0000

Data Index: 545408 (The Pile)

Max Activating Token Index: 705