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

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

Neuron 751 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: 1.5939. Min Range: -1.5939

Max Act: 1.5316. Min Act: -0.0001

Data Index: 392428 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.5144. Min Act: -0.0001

Data Index: 1266303 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.5939. Min Act: -0.0001

Data Index: 629688 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.4164. Min Act: -0.0001

Data Index: 1317545 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.4543. Min Act: -0.0001

Data Index: 1162039 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.4439. Min Act: -0.0001

Data Index: 934991 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3888. Min Act: -0.0001

Data Index: 1312229 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3520. Min Act: -0.0001

Data Index: 191445 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3684. Min Act: -0.0001

Data Index: 517963 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3394. Min Act: -0.0001

Data Index: 1218322 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3314. Min Act: -0.0001

Data Index: 462160 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.3614. Min Act: -0.0001

Data Index: 1120723 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2821. Min Act: -0.0001

Data Index: 399808 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2748. Min Act: -0.0001

Data Index: 584093 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2575. Min Act: -0.0001

Data Index: 1146563 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2131. Min Act: -0.0001

Data Index: 316911 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2097. Min Act: -0.0001

Data Index: 464551 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.2078. Min Act: -0.0001

Data Index: 588383 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.5939. Min Range: -1.5939

Max Act: 1.1946. Min Act: -0.0001

Data Index: 1156607 (C4 (Web Text))

Max Activating Token Index: 114