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

Dataset: The Pile

Neuron 1984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.4233. Min Act: -0.0000

Data Index: 985253 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 1.4233. Min Range: -1.4233

Max Act: 1.0391. Min Act: -0.0000

Data Index: 1418111 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.9804. Min Act: -0.0000

Data Index: 1283129 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8844. Min Act: -0.0000

Data Index: 874260 (The Pile)

Max Activating Token Index: 366

Text #4

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8337. Min Act: -0.0000

Data Index: 361141 (The Pile)

Max Activating Token Index: 703

Text #5

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8249. Min Act: -0.0000

Data Index: 1856100 (The Pile)

Max Activating Token Index: 1009

Text #6

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7844. Min Act: -0.0000

Data Index: 929541 (The Pile)

Max Activating Token Index: 861

Text #7

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7849. Min Act: -0.0000

Data Index: 742645 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1963235 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7313. Min Act: -0.0000

Data Index: 315662 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7342. Min Act: -0.0000

Data Index: 1531360 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7337. Min Act: -0.0000

Data Index: 563584 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7444. Min Act: -0.0000

Data Index: 1857904 (The Pile)

Max Activating Token Index: 818

Text #13

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7095. Min Act: -0.0000

Data Index: 192253 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7643. Min Act: -0.0000

Data Index: 824993 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1493648 (The Pile)

Max Activating Token Index: 335

Text #16

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7120. Min Act: -0.0000

Data Index: 129440 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1261439 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.7509. Min Act: -0.0000

Data Index: 271255 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 1.4233. Min Range: -1.4233

Max Act: 0.6939. Min Act: -0.0000

Data Index: 300441 (The Pile)

Max Activating Token Index: 936