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

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

Neuron 3694 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: 0.8189. Min Range: -0.8189

Max Act: 0.8007. Min Act: -0.0001

Data Index: 8923 (C4 (Web Text))

Max Activating Token Index: 248

Text #1

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.8189. Min Act: -0.0001

Data Index: 896507 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7489. Min Act: -0.0001

Data Index: 995025 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5957. Min Act: -0.0001

Data Index: 880930 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7361. Min Act: -0.0001

Data Index: 531797 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6666. Min Act: -0.0001

Data Index: 1558319 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.7226. Min Act: -0.0001

Data Index: 216105 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6126. Min Act: -0.0001

Data Index: 80776 (C4 (Web Text))

Max Activating Token Index: 725

Text #8

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6181. Min Act: -0.0001

Data Index: 1634258 (Python Code)

Max Activating Token Index: 992

Text #9

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6362. Min Act: -0.0001

Data Index: 1104400 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6135. Min Act: -0.0001

Data Index: 359277 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6285. Min Act: -0.0001

Data Index: 70024 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6933. Min Act: -0.0001

Data Index: 529144 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6157. Min Act: -0.0001

Data Index: 616650 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1141544 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5924. Min Act: -0.0001

Data Index: 1477978 (Python Code)

Max Activating Token Index: 1022

Text #16

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5683. Min Act: -0.0001

Data Index: 1234536 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5157. Min Act: -0.0001

Data Index: 631455 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.5277. Min Act: -0.0001

Data Index: 228620 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.8189. Min Range: -0.8189

Max Act: 0.6205. Min Act: -0.0001

Data Index: 891716 (C4 (Web Text))

Max Activating Token Index: 941