Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.5225. Min Act: -0.0001

Data Index: 998394 (C4 (Web Text))

Max Activating Token Index: 276

Text #1

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4294. Min Act: -0.0001

Data Index: 244120 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4367. Min Act: -0.0001

Data Index: 525608 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4108. Min Act: -0.0001

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4317. Min Act: -0.0001

Data Index: 1163502 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4110. Min Act: -0.0001

Data Index: 84942 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4547. Min Act: -0.0001

Data Index: 960495 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4285. Min Act: -0.0001

Data Index: 615488 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4139. Min Act: -0.0001

Data Index: 824036 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4115. Min Act: -0.0001

Data Index: 624995 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3873. Min Act: -0.0001

Data Index: 516715 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4046. Min Act: -0.0001

Data Index: 63637 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3931. Min Act: -0.0001

Data Index: 802001 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3885. Min Act: -0.0001

Data Index: 968488 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3595. Min Act: -0.0001

Data Index: 83310 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3956. Min Act: -0.0001

Data Index: 866921 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3935. Min Act: -0.0001

Data Index: 67401 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.4010. Min Act: -0.0001

Data Index: 706924 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3796. Min Act: -0.0001

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 0.5225. Min Range: -0.5225

Max Act: 0.3780. Min Act: -0.0001

Data Index: 663025 (C4 (Web Text))

Max Activating Token Index: 929