Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2823. Min Range: -5.2823

Max Act: 5.2823. Min Act: -0.0000

Data Index: 1115287 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.3862. Min Act: -0.0000

Data Index: 222912 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.1784. Min Act: -0.0000

Data Index: 1203582 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.3039. Min Act: -0.0001

Data Index: 447232 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.1356. Min Act: -0.0000

Data Index: 950266 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.4428. Min Act: -0.0000

Data Index: 252250 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.2746. Min Act: -0.0000

Data Index: 97409 (C4 (Web Text))

Max Activating Token Index: 581

Text #7

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.1409. Min Act: -0.0001

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.9560. Min Act: -0.0001

Data Index: 97974 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.0997. Min Act: -0.0000

Data Index: 794303 (C4 (Web Text))

Max Activating Token Index: 584

Text #10

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.1123. Min Act: -0.0001

Data Index: 950464 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.0731. Min Act: -0.0001

Data Index: 749398 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.1171. Min Act: -0.0000

Data Index: 398611 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.0857. Min Act: -0.0001

Data Index: 1254561 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 5.2823. Min Range: -5.2823

Max Act: 4.2079. Min Act: -0.0001

Data Index: 814068 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.5970. Min Act: -0.0000

Data Index: 114061 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.6645. Min Act: -0.0000

Data Index: 254450 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.8591. Min Act: -0.0000

Data Index: 459572 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.7258. Min Act: -0.0000

Data Index: 518067 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 5.2823. Min Range: -5.2823

Max Act: 3.5074. Min Act: -0.0000

Data Index: 708244 (C4 (Web Text))

Max Activating Token Index: 775