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

Dataset: The Pile

Neuron 3097 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: 1.4442. Min Range: -1.4442

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1526198 (The Pile)

Max Activating Token Index: 856

Text #1

Max Range: 1.4442. Min Range: -1.4442

Max Act: 1.0164. Min Act: -0.0000

Data Index: 632713 (The Pile)

Max Activating Token Index: 964

Text #2

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1973274 (The Pile)

Max Activating Token Index: 903

Text #3

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.9691. Min Act: -0.0000

Data Index: 117686 (The Pile)

Max Activating Token Index: 468

Text #4

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1137473 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.9375. Min Act: -0.0000

Data Index: 1460000 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.9743. Min Act: -0.0000

Data Index: 202011 (The Pile)

Max Activating Token Index: 740

Text #7

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1263057 (The Pile)

Max Activating Token Index: 269

Text #8

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1082262 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8361. Min Act: -0.0000

Data Index: 585375 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8196. Min Act: -0.0000

Data Index: 822664 (The Pile)

Max Activating Token Index: 288

Text #11

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1890208 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1765381 (The Pile)

Max Activating Token Index: 153

Text #13

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.7772. Min Act: -0.0000

Data Index: 794345 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8142. Min Act: -0.0000

Data Index: 211838 (The Pile)

Max Activating Token Index: 402

Text #15

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8057. Min Act: -0.0000

Data Index: 181178 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.8067. Min Act: -0.0000

Data Index: 989456 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.7942. Min Act: -0.0000

Data Index: 320249 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.7948. Min Act: -0.0000

Data Index: 24492 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 1.4442. Min Range: -1.4442

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1593766 (The Pile)

Max Activating Token Index: 607