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

Dataset: The Pile

Neuron 547 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2884. Min Act: -0.0000

Data Index: 219773 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.4271. Min Act: -0.0000

Data Index: 556081 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.3878. Min Act: -0.0000

Data Index: 1338325 (The Pile)

Max Activating Token Index: 435

Text #3

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.1193. Min Act: -0.0000

Data Index: 924902 (The Pile)

Max Activating Token Index: 100

Text #4

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.1581. Min Act: -0.0000

Data Index: 1738455 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.7276. Min Act: -0.0000

Data Index: 152265 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.6989. Min Act: -0.0000

Data Index: 275907 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.3580. Min Act: -0.0000

Data Index: 484944 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2955. Min Act: -0.0000

Data Index: 595096 (The Pile)

Max Activating Token Index: 919

Text #9

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2191. Min Act: -0.0000

Data Index: 1533154 (The Pile)

Max Activating Token Index: 196

Text #10

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.1197. Min Act: -0.0000

Data Index: 805738 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2555. Min Act: -0.0000

Data Index: 1363206 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.5472. Min Act: -0.0000

Data Index: 1726470 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2045. Min Act: -0.0000

Data Index: 1800376 (The Pile)

Max Activating Token Index: 442

Text #14

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2605. Min Act: -0.0000

Data Index: 896528 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2605. Min Act: -0.0000

Data Index: 1974717 (The Pile)

Max Activating Token Index: 275

Text #16

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.1261. Min Act: -0.0000

Data Index: 1938964 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.5787. Min Act: -0.0000

Data Index: 136406 (The Pile)

Max Activating Token Index: 885

Text #18

Max Range: 3.7276. Min Range: -3.7276

Max Act: 3.2855. Min Act: -0.0000

Data Index: 76776 (The Pile)

Max Activating Token Index: 875

Text #19

Max Range: 3.7276. Min Range: -3.7276

Max Act: 2.6698. Min Act: -0.0000

Data Index: 770179 (The Pile)

Max Activating Token Index: 994