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

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

Neuron 3307 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.7290. Min Act: -0.0001

Data Index: 392151 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6645. Min Act: -0.0001

Data Index: 1096963 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6545. Min Act: -0.0001

Data Index: 861991 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6713. Min Act: -0.0001

Data Index: 596325 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6268. Min Act: -0.0001

Data Index: 1163677 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6406. Min Act: -0.0001

Data Index: 1241153 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1166389 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5784. Min Act: -0.0001

Data Index: 57259 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5947. Min Act: -0.0001

Data Index: 1193554 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6241. Min Act: -0.0001

Data Index: 28169 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6423. Min Act: -0.0001

Data Index: 1176421 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5883. Min Act: -0.0001

Data Index: 437097 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6206. Min Act: -0.0001

Data Index: 815513 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6226. Min Act: -0.0001

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5757. Min Act: -0.0001

Data Index: 476343 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5969. Min Act: -0.0001

Data Index: 845893 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6162. Min Act: -0.0001

Data Index: 967005 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5964. Min Act: -0.0001

Data Index: 165578 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.6099. Min Act: -0.0001

Data Index: 376795 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.7290. Min Range: -0.7290

Max Act: 0.5761. Min Act: -0.0001

Data Index: 909395 (C4 (Web Text))

Max Activating Token Index: 860