Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 718 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.7512. Min Act: -0.0001

Data Index: 1227327 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6749. Min Act: -0.0001

Data Index: 85110 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6580. Min Act: -0.0001

Data Index: 1306402 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6682. Min Act: -0.0001

Data Index: 260814 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6490. Min Act: -0.0001

Data Index: 1176987 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6420. Min Act: -0.0001

Data Index: 1105658 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6137. Min Act: -0.0001

Data Index: 414081 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6048. Min Act: -0.0001

Data Index: 104372 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6079. Min Act: -0.0001

Data Index: 464562 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6263. Min Act: -0.0001

Data Index: 1337476 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5993. Min Act: -0.0001

Data Index: 532190 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6283. Min Act: -0.0001

Data Index: 824836 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.6156. Min Act: -0.0001

Data Index: 22938 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5663. Min Act: -0.0001

Data Index: 600013 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5711. Min Act: -0.0001

Data Index: 424307 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5884. Min Act: -0.0001

Data Index: 600286 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5779. Min Act: -0.0001

Data Index: 716438 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5573. Min Act: -0.0001

Data Index: 1109363 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5783. Min Act: -0.0001

Data Index: 6195 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.7512. Min Range: -0.7512

Max Act: 0.5937. Min Act: -0.0001

Data Index: 889238 (C4 (Web Text))

Max Activating Token Index: 59