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

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

Neuron 2027 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: 0.9847. Min Range: -0.9847

Max Act: 0.9847. Min Act: -0.0001

Data Index: 707019 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8954. Min Act: -0.0001

Data Index: 488619 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8922. Min Act: -0.0001

Data Index: 359627 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8447. Min Act: -0.0001

Data Index: 524294 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8857. Min Act: -0.0001

Data Index: 297124 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7866. Min Act: -0.0001

Data Index: 80997 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7443. Min Act: -0.0001

Data Index: 867702 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7810. Min Act: -0.0001

Data Index: 674384 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8021. Min Act: -0.0001

Data Index: 1289484 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.8491. Min Act: -0.0001

Data Index: 160153 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7821. Min Act: -0.0001

Data Index: 1078850 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7829. Min Act: -0.0001

Data Index: 291410 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1041831 (C4 (Web Text))

Max Activating Token Index: 242

Text #13

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7473. Min Act: -0.0001

Data Index: 1553188 (Python Code)

Max Activating Token Index: 634

Text #14

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.6869. Min Act: -0.0001

Data Index: 1089884 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7430. Min Act: -0.0001

Data Index: 865646 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7228. Min Act: -0.0001

Data Index: 1327351 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7172. Min Act: -0.0001

Data Index: 673527 (C4 (Web Text))

Max Activating Token Index: 3

Text #18

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7135. Min Act: -0.0001

Data Index: 1135140 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 0.9847. Min Range: -0.9847

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1094897 (C4 (Web Text))

Max Activating Token Index: 757