Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1722729 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7322. Min Act: -0.0000

Data Index: 1905189 (The Pile)

Max Activating Token Index: 772

Text #2

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7569. Min Act: -0.0000

Data Index: 1868592 (The Pile)

Max Activating Token Index: 158

Text #3

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7631. Min Act: -0.0000

Data Index: 39069 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7926. Min Act: -0.0000

Data Index: 915239 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7251. Min Act: -0.0000

Data Index: 1127267 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1845911 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6037. Min Act: -0.0000

Data Index: 821733 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6633. Min Act: -0.0000

Data Index: 1302307 (The Pile)

Max Activating Token Index: 89

Text #9

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5927. Min Act: -0.0000

Data Index: 1284357 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6532. Min Act: -0.0000

Data Index: 610105 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1381197 (The Pile)

Max Activating Token Index: 158

Text #12

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6098. Min Act: -0.0000

Data Index: 585746 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5983. Min Act: -0.0000

Data Index: 255954 (The Pile)

Max Activating Token Index: 222

Text #14

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1879047 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6095. Min Act: -0.0000

Data Index: 1761488 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6178. Min Act: -0.0000

Data Index: 8248 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5820. Min Act: -0.0000

Data Index: 1855212 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5861. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 271

Text #19

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5921. Min Act: -0.0000

Data Index: 431700 (The Pile)

Max Activating Token Index: 253