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

Dataset: The Pile

Neuron 1563 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.2293. Min Act: -0.0000

Data Index: 1434442 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.1501. Min Act: -0.0000

Data Index: 1889952 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0162. Min Act: -0.0000

Data Index: 320608 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1572735 (The Pile)

Max Activating Token Index: 703

Text #4

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9737. Min Act: -0.0000

Data Index: 588360 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1267366 (The Pile)

Max Activating Token Index: 202

Text #6

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8635. Min Act: -0.0000

Data Index: 1806776 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1357843 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9451. Min Act: -0.0000

Data Index: 168363 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 1.2293. Min Range: -1.2293

Max Act: 1.0066. Min Act: -0.0000

Data Index: 1803213 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9318. Min Act: -0.0000

Data Index: 225314 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8535. Min Act: -0.0000

Data Index: 858576 (The Pile)

Max Activating Token Index: 842

Text #12

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.9249. Min Act: -0.0000

Data Index: 1257254 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.7900. Min Act: -0.0000

Data Index: 878913 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8180. Min Act: -0.0000

Data Index: 733878 (The Pile)

Max Activating Token Index: 379

Text #15

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8479. Min Act: -0.0000

Data Index: 27167 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8250. Min Act: -0.0000

Data Index: 907028 (The Pile)

Max Activating Token Index: 61

Text #17

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.7320. Min Act: -0.0000

Data Index: 627400 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.8142. Min Act: -0.0000

Data Index: 601927 (The Pile)

Max Activating Token Index: 1020

Text #19

Max Range: 1.2293. Min Range: -1.2293

Max Act: 0.7888. Min Act: -0.0000

Data Index: 232790 (The Pile)

Max Activating Token Index: 872