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

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

Neuron 786 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1207408 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.6302. Min Act: -0.0000

Data Index: 184206 (C4 (Web Text))

Max Activating Token Index: 768

Text #2

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5865. Min Act: -0.0000

Data Index: 598402 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5676. Min Act: -0.0001

Data Index: 111307 (C4 (Web Text))

Max Activating Token Index: 271

Text #4

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5462. Min Act: -0.0001

Data Index: 193952 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5519. Min Act: -0.0001

Data Index: 85919 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5224. Min Act: -0.0001

Data Index: 718365 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5399. Min Act: -0.0001

Data Index: 247066 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5189. Min Act: -0.0001

Data Index: 566680 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5145. Min Act: -0.0000

Data Index: 531104 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5088. Min Act: -0.0001

Data Index: 939149 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.5209. Min Act: -0.0001

Data Index: 588040 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4833. Min Act: -0.0001

Data Index: 842708 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4945. Min Act: -0.0001

Data Index: 995624 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4877. Min Act: -0.0001

Data Index: 1234479 (C4 (Web Text))

Max Activating Token Index: 734

Text #15

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1110037 (C4 (Web Text))

Max Activating Token Index: 457

Text #16

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4594. Min Act: -0.0001

Data Index: 308162 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4455. Min Act: -0.0001

Data Index: 1379488 (Python Code)

Max Activating Token Index: 528

Text #18

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4542. Min Act: -0.0000

Data Index: 377691 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.6488. Min Range: -0.6488

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1096130 (C4 (Web Text))

Max Activating Token Index: 662