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

Dataset: The Pile

Neuron 2348 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: 4.6208. Min Range: -4.6208

Max Act: 4.6208. Min Act: -0.0000

Data Index: 403828 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.3220. Min Act: -0.0000

Data Index: 1928185 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.2999. Min Act: -0.0000

Data Index: 749061 (The Pile)

Max Activating Token Index: 243

Text #3

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.2779. Min Act: -0.0000

Data Index: 1842196 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.1331. Min Act: -0.0000

Data Index: 1672319 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.9000. Min Act: -0.0000

Data Index: 1880207 (The Pile)

Max Activating Token Index: 75

Text #6

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.0255. Min Act: -0.0000

Data Index: 542562 (The Pile)

Max Activating Token Index: 176

Text #7

Max Range: 4.6208. Min Range: -4.6208

Max Act: 4.0107. Min Act: -0.0000

Data Index: 1511674 (The Pile)

Max Activating Token Index: 124

Text #8

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.9559. Min Act: -0.0000

Data Index: 1579767 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.9338. Min Act: -0.0000

Data Index: 1741536 (The Pile)

Max Activating Token Index: 89

Text #10

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.9028. Min Act: -0.0000

Data Index: 666065 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8895. Min Act: -0.0000

Data Index: 1193162 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.7206. Min Act: -0.0000

Data Index: 903752 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8732. Min Act: -0.0000

Data Index: 689078 (The Pile)

Max Activating Token Index: 271

Text #14

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8410. Min Act: -0.0000

Data Index: 1848072 (The Pile)

Max Activating Token Index: 123

Text #15

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8257. Min Act: -0.0000

Data Index: 924804 (The Pile)

Max Activating Token Index: 448

Text #16

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8281. Min Act: -0.0000

Data Index: 770836 (The Pile)

Max Activating Token Index: 271

Text #17

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.8126. Min Act: -0.0000

Data Index: 27061 (The Pile)

Max Activating Token Index: 385

Text #18

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.9621. Min Act: -0.0000

Data Index: 378724 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 4.6208. Min Range: -4.6208

Max Act: 3.7774. Min Act: -0.0000

Data Index: 1956112 (The Pile)

Max Activating Token Index: 499