Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2988 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 8.3369. Min Range: -8.3369

Max Act: 8.3369. Min Act: -0.0000

Data Index: 173852 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.9665. Min Act: -0.0000

Data Index: 20530 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.9930. Min Act: -0.0000

Data Index: 366846 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.6008. Min Act: -0.0000

Data Index: 1301112 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.6583. Min Act: -0.0000

Data Index: 589854 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.4681. Min Act: -0.0000

Data Index: 122386 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.3946. Min Act: 0.0001

Data Index: 323830 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.3825. Min Act: 0.0001

Data Index: 1152476 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.1271. Min Act: -0.0000

Data Index: 1067836 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.3351. Min Act: -0.0000

Data Index: 857712 (C4 (Web Text))

Max Activating Token Index: 888

Text #10

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.8193. Min Act: 0.0005

Data Index: 499637 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.9725. Min Act: 0.0001

Data Index: 437121 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 8.3369. Min Range: -8.3369

Max Act: 7.0416. Min Act: -0.0000

Data Index: 677591 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.9561. Min Act: -0.0000

Data Index: 363108 (C4 (Web Text))

Max Activating Token Index: 240

Text #14

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.7722. Min Act: -0.0000

Data Index: 992767 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.7587. Min Act: -0.0000

Data Index: 1326428 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.7419. Min Act: 0.0006

Data Index: 394183 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.7158. Min Act: -0.0000

Data Index: 23647 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.8695. Min Act: -0.0000

Data Index: 764409 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 8.3369. Min Range: -8.3369

Max Act: 6.8683. Min Act: 0.0000

Data Index: 641237 (C4 (Web Text))

Max Activating Token Index: 494