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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2378 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.6157. Min Act: -0.0001

Data Index: 1024417 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5337. Min Act: -0.0001

Data Index: 183922 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5186. Min Act: -0.0001

Data Index: 59722 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5056. Min Act: -0.0001

Data Index: 1211984 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5039. Min Act: -0.0001

Data Index: 557284 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5374. Min Act: -0.0001

Data Index: 517931 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5101. Min Act: -0.0001

Data Index: 171470 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.5122. Min Act: -0.0001

Data Index: 600368 (C4 (Web Text))

Max Activating Token Index: 604

Text #8

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4862. Min Act: -0.0001

Data Index: 331976 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4598. Min Act: -0.0001

Data Index: 214906 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4715. Min Act: -0.0001

Data Index: 140647 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4451. Min Act: -0.0001

Data Index: 293980 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4547. Min Act: -0.0001

Data Index: 739118 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4854. Min Act: -0.0001

Data Index: 1212739 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4497. Min Act: -0.0001

Data Index: 813543 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4367. Min Act: -0.0001

Data Index: 528787 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4462. Min Act: -0.0001

Data Index: 1263779 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4544. Min Act: -0.0001

Data Index: 1134187 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4515. Min Act: -0.0001

Data Index: 134133 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.6157. Min Range: -0.6157

Max Act: 0.4214. Min Act: -0.0001

Data Index: 160095 (C4 (Web Text))

Max Activating Token Index: 554