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

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

Neuron 1594 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: 0.4075. Min Range: -0.4075

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1102930 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1339328 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1033550 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3741. Min Act: -0.0001

Data Index: 588262 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3595. Min Act: -0.0000

Data Index: 963300 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3677. Min Act: -0.0000

Data Index: 526620 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3571. Min Act: -0.0000

Data Index: 246220 (C4 (Web Text))

Max Activating Token Index: 601

Text #7

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3693. Min Act: -0.0001

Data Index: 801009 (C4 (Web Text))

Max Activating Token Index: 100

Text #8

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1250812 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3490. Min Act: -0.0000

Data Index: 864996 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3423. Min Act: -0.0001

Data Index: 1233643 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3434. Min Act: -0.0001

Data Index: 710686 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1108748 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1324382 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3352. Min Act: -0.0000

Data Index: 213159 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3219. Min Act: -0.0000

Data Index: 995588 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1144739 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3155. Min Act: -0.0000

Data Index: 353042 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3095. Min Act: -0.0000

Data Index: 433609 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 0.4075. Min Range: -0.4075

Max Act: 0.3177. Min Act: -0.0001

Data Index: 675693 (C4 (Web Text))

Max Activating Token Index: 779