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

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

Neuron 3208 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: 3.3990. Min Range: -3.3990

Max Act: 3.3990. Min Act: -0.0001

Data Index: 970246 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.9207. Min Act: -0.0001

Data Index: 672974 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.7416. Min Act: -0.0001

Data Index: 328715 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.8224. Min Act: -0.0000

Data Index: 627280 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.7753. Min Act: -0.0001

Data Index: 1272680 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.5668. Min Act: -0.0001

Data Index: 495935 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.5991. Min Act: -0.0001

Data Index: 494651 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.5922. Min Act: -0.0001

Data Index: 453260 (C4 (Web Text))

Max Activating Token Index: 992

Text #8

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4227. Min Act: -0.0001

Data Index: 1234250 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4967. Min Act: -0.0001

Data Index: 834655 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.5036. Min Act: -0.0000

Data Index: 302327 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4706. Min Act: -0.0001

Data Index: 1353829 (C4 (Web Text))

Max Activating Token Index: 15

Text #12

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.3342. Min Act: -0.0001

Data Index: 364735 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4598. Min Act: -0.0001

Data Index: 285552 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.3285. Min Act: -0.0001

Data Index: 48932 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4089. Min Act: -0.0000

Data Index: 610576 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.2863. Min Act: -0.0001

Data Index: 1079207 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.4059. Min Act: -0.0001

Data Index: 1224218 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.3981. Min Act: -0.0001

Data Index: 873248 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 3.3990. Min Range: -3.3990

Max Act: 2.2527. Min Act: -0.0001

Data Index: 261706 (C4 (Web Text))

Max Activating Token Index: 216