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

Dataset: The Pile

Neuron 2746 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1276. Min Range: -1.1276

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1536687 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9931. Min Act: -0.0000

Data Index: 668573 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9892. Min Act: -0.0000

Data Index: 1853531 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9426. Min Act: -0.0000

Data Index: 1235415 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9123. Min Act: -0.0000

Data Index: 267340 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9214. Min Act: -0.0000

Data Index: 554890 (The Pile)

Max Activating Token Index: 941

Text #6

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.9123. Min Act: -0.0000

Data Index: 864862 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8374. Min Act: -0.0000

Data Index: 794678 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1242257 (The Pile)

Max Activating Token Index: 440

Text #9

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8127. Min Act: -0.0000

Data Index: 549205 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8287. Min Act: -0.0000

Data Index: 344398 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1543756 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7578. Min Act: -0.0000

Data Index: 430513 (The Pile)

Max Activating Token Index: 232

Text #13

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7875. Min Act: -0.0000

Data Index: 1890377 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.8054. Min Act: -0.0000

Data Index: 188908 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7925. Min Act: -0.0000

Data Index: 668906 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7846. Min Act: -0.0000

Data Index: 651888 (The Pile)

Max Activating Token Index: 748

Text #17

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7776. Min Act: -0.0000

Data Index: 630400 (The Pile)

Max Activating Token Index: 928

Text #18

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7777. Min Act: -0.0000

Data Index: 988485 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.1276. Min Range: -1.1276

Max Act: 0.7735. Min Act: -0.0000

Data Index: 399936 (The Pile)

Max Activating Token Index: 479