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

Dataset: The Pile

Neuron 359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2739. Min Act: -0.0000

Data Index: 503453 (The Pile)

Max Activating Token Index: 587

Text #1

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2769. Min Act: -0.0000

Data Index: 723580 (The Pile)

Max Activating Token Index: 184

Text #2

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2420. Min Act: -0.0000

Data Index: 878256 (The Pile)

Max Activating Token Index: 381

Text #3

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2364. Min Act: -0.0000

Data Index: 859371 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2362. Min Act: -0.0000

Data Index: 351192 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1319796 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2297. Min Act: -0.0000

Data Index: 321191 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1360094 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2555. Min Act: -0.0000

Data Index: 588271 (The Pile)

Max Activating Token Index: 624

Text #9

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2287. Min Act: -0.0000

Data Index: 58289 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2058. Min Act: -0.0000

Data Index: 667154 (The Pile)

Max Activating Token Index: 910

Text #11

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2252. Min Act: -0.0000

Data Index: 509316 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1406701 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1800616 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1010538 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1934548 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1306500 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1124871 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1474316 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 0.2769. Min Range: -0.2769

Max Act: 0.1992. Min Act: -0.0000

Data Index: 156179 (The Pile)

Max Activating Token Index: 177