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

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

Neuron 869 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.4091. Min Act: -0.0001

Data Index: 1114426 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.5265. Min Act: -0.0001

Data Index: 986056 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.4172. Min Act: -0.0001

Data Index: 913599 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.2448. Min Act: -0.0001

Data Index: 857702 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.8313. Min Act: -0.0001

Data Index: 1200309 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.3819. Min Act: -0.0001

Data Index: 933654 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.1259. Min Act: -0.0001

Data Index: 393755 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.1084. Min Act: -0.0001

Data Index: 124282 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.8659. Min Act: -0.0001

Data Index: 1227192 (C4 (Web Text))

Max Activating Token Index: 530

Text #9

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.7010. Min Act: -0.0001

Data Index: 932116 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.0198. Min Act: -0.0001

Data Index: 487507 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.6599. Min Act: -0.0001

Data Index: 552892 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.8464. Min Act: -0.0001

Data Index: 644781 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.0654. Min Act: -0.0001

Data Index: 543776 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.0326. Min Act: -0.0001

Data Index: 205091 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.8735. Min Act: -0.0001

Data Index: 728667 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 5.5265. Min Range: -5.5265

Max Act: 5.1985. Min Act: -0.0001

Data Index: 162386 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.7806. Min Act: -0.0001

Data Index: 897109 (C4 (Web Text))

Max Activating Token Index: 881

Text #18

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.7440. Min Act: -0.0001

Data Index: 698762 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 5.5265. Min Range: -5.5265

Max Act: 4.7163. Min Act: -0.0001

Data Index: 833604 (C4 (Web Text))

Max Activating Token Index: 319