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

Dataset: The Pile

Neuron 2541 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: 0.7223. Min Range: -0.7223

Max Act: 0.7223. Min Act: -0.0000

Data Index: 457809 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6539. Min Act: -0.0000

Data Index: 1771234 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5901. Min Act: -0.0000

Data Index: 571111 (The Pile)

Max Activating Token Index: 853

Text #3

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1789081 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1832596 (The Pile)

Max Activating Token Index: 1000

Text #5

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1181575 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6089. Min Act: -0.0000

Data Index: 523417 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5962. Min Act: -0.0000

Data Index: 261857 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1742984 (The Pile)

Max Activating Token Index: 269

Text #9

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6042. Min Act: -0.0000

Data Index: 792525 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.6065. Min Act: -0.0000

Data Index: 927178 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5817. Min Act: -0.0000

Data Index: 1292010 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5453. Min Act: -0.0000

Data Index: 396742 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5254. Min Act: -0.0000

Data Index: 514280 (The Pile)

Max Activating Token Index: 139

Text #14

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5413. Min Act: -0.0000

Data Index: 507388 (The Pile)

Max Activating Token Index: 58

Text #15

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5389. Min Act: -0.0000

Data Index: 843633 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5482. Min Act: -0.0000

Data Index: 1934861 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5269. Min Act: -0.0000

Data Index: 351835 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5288. Min Act: -0.0000

Data Index: 909192 (The Pile)

Max Activating Token Index: 947

Text #19

Max Range: 0.7223. Min Range: -0.7223

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1070023 (The Pile)

Max Activating Token Index: 966