Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2436. Min Range: -4.2436

Max Act: 4.2436. Min Act: -0.0001

Data Index: 185790 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 4.2436. Min Range: -4.2436

Max Act: 4.1064. Min Act: -0.0001

Data Index: 409444 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3218. Min Act: -0.0001

Data Index: 993656 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.4683. Min Act: -0.0001

Data Index: 772946 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.8596. Min Act: -0.0001

Data Index: 989531 (C4 (Web Text))

Max Activating Token Index: 138

Text #5

Max Range: 4.2436. Min Range: -4.2436

Max Act: 2.9431. Min Act: -0.0001

Data Index: 718875 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3700. Min Act: -0.0001

Data Index: 367276 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3599. Min Act: -0.0001

Data Index: 484824 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3620. Min Act: -0.0000

Data Index: 783932 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3620. Min Act: -0.0000

Data Index: 541228 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.5014. Min Act: -0.0000

Data Index: 1298536 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.1786. Min Act: -0.0001

Data Index: 578399 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.6502. Min Act: -0.0001

Data Index: 1354814 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.1849. Min Act: -0.0000

Data Index: 136710 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.3362. Min Act: -0.0001

Data Index: 288319 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.4610. Min Act: -0.0001

Data Index: 761140 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.1511. Min Act: -0.0001

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.5749. Min Act: -0.0001

Data Index: 333 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.2667. Min Act: -0.0001

Data Index: 654389 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 4.2436. Min Range: -4.2436

Max Act: 3.4040. Min Act: -0.0001

Data Index: 564575 (C4 (Web Text))

Max Activating Token Index: 991