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

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

Neuron 4320 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6071. Min Act: -0.0000

Data Index: 781279 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6593. Min Act: -0.0000

Data Index: 954778 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6922. Min Act: -0.0000

Data Index: 268712 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.6170. Min Act: -0.0000

Data Index: 750735 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.5479. Min Act: -0.0000

Data Index: 161098 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1231247 (C4 (Web Text))

Max Activating Token Index: 294

Text #6

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.4991. Min Act: -0.0000

Data Index: 509374 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.4047. Min Act: -0.0000

Data Index: 76708 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1182304 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.3567. Min Act: -0.0000

Data Index: 582690 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2952. Min Act: -0.0000

Data Index: 274291 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1002 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.3514. Min Act: -0.0000

Data Index: 74240 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.3159. Min Act: -0.0000

Data Index: 274043 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.3248. Min Act: -0.0000

Data Index: 947408 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2831. Min Act: -0.0000

Data Index: 988276 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1126413 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2595. Min Act: -0.0000

Data Index: 821308 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2771. Min Act: -0.0000

Data Index: 1584356 (Python Code)

Max Activating Token Index: 257

Text #19

Max Range: 0.6922. Min Range: -0.6922

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1089979 (C4 (Web Text))

Max Activating Token Index: 967