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

Dataset: The Pile

Neuron 4611 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1844744 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.5995. Min Act: -0.0000

Data Index: 217598 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.4956. Min Act: -0.0000

Data Index: 1697100 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.6048. Min Act: -0.0000

Data Index: 1235723 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.4158. Min Act: -0.0000

Data Index: 1052209 (The Pile)

Max Activating Token Index: 758

Text #5

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.1469. Min Act: -0.0000

Data Index: 855212 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.0936. Min Act: -0.0000

Data Index: 997846 (The Pile)

Max Activating Token Index: 301

Text #7

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.1235. Min Act: -0.0000

Data Index: 205515 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.0987. Min Act: -0.0000

Data Index: 1935257 (The Pile)

Max Activating Token Index: 453

Text #9

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.0301. Min Act: -0.0000

Data Index: 40113 (The Pile)

Max Activating Token Index: 169

Text #10

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1663065 (The Pile)

Max Activating Token Index: 367

Text #11

Max Range: 1.6132. Min Range: -1.6132

Max Act: 1.0111. Min Act: -0.0000

Data Index: 1949081 (The Pile)

Max Activating Token Index: 512

Text #12

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1527395 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.9404. Min Act: -0.0000

Data Index: 1272093 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1913326 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.9189. Min Act: -0.0000

Data Index: 889529 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1065129 (The Pile)

Max Activating Token Index: 54

Text #17

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.8984. Min Act: -0.0000

Data Index: 718935 (The Pile)

Max Activating Token Index: 88

Text #18

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.9220. Min Act: -0.0000

Data Index: 965682 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 1.6132. Min Range: -1.6132

Max Act: 0.8900. Min Act: -0.0000

Data Index: 1315538 (The Pile)

Max Activating Token Index: 345