Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1166 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5331. Min Range: -2.5331

Max Act: 2.5331. Min Act: -0.0000

Data Index: 490139 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 2.5331. Min Range: -2.5331

Max Act: 2.1169. Min Act: -0.0000

Data Index: 121312 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 2.5331. Min Range: -2.5331

Max Act: 2.0334. Min Act: -0.0000

Data Index: 538257 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.7681. Min Act: -0.0001

Data Index: 1549128 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.8595. Min Act: -0.0000

Data Index: 794222 (C4 (Web Text))

Max Activating Token Index: 569

Text #5

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.9120. Min Act: -0.0000

Data Index: 1132379 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.7156. Min Act: -0.0001

Data Index: 514068 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.8027. Min Act: -0.0000

Data Index: 866940 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.9450. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.6974. Min Act: -0.0000

Data Index: 954146 (C4 (Web Text))

Max Activating Token Index: 508

Text #10

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1103599 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4905. Min Act: -0.0000

Data Index: 1605057 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1623024 (Python Code)

Max Activating Token Index: 453

Text #13

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.7287. Min Act: -0.0000

Data Index: 1508861 (Python Code)

Max Activating Token Index: 297

Text #14

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.5701. Min Act: -0.0000

Data Index: 1436612 (Python Code)

Max Activating Token Index: 320

Text #15

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.6134. Min Act: -0.0000

Data Index: 1551399 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.5394. Min Act: -0.0000

Data Index: 895256 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1240114 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4907. Min Act: -0.0000

Data Index: 786219 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 2.5331. Min Range: -2.5331

Max Act: 1.4379. Min Act: -0.0000

Data Index: 127448 (C4 (Web Text))

Max Activating Token Index: 1019