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

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

Neuron 4485 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4230. Min Range: -1.4230

Max Act: 1.4230. Min Act: 0.0000

Data Index: 198424 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 1.4230. Min Range: -1.4230

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1111044 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.9819. Min Act: 0.0000

Data Index: 727909 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1349145 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1308051 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.8187. Min Act: 0.0000

Data Index: 1047295 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.8077. Min Act: 0.0000

Data Index: 575315 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6897. Min Act: 0.0000

Data Index: 271797 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7274. Min Act: 0.0000

Data Index: 85982 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7575. Min Act: -0.0000

Data Index: 1208874 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7524. Min Act: 0.0000

Data Index: 415263 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7453. Min Act: 0.0001

Data Index: 221718 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7324. Min Act: 0.0000

Data Index: 149192 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6863. Min Act: -0.0000

Data Index: 212445 (C4 (Web Text))

Max Activating Token Index: 798

Text #14

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6653. Min Act: -0.0000

Data Index: 498303 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1006132 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6598. Min Act: 0.0000

Data Index: 297087 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.7170. Min Act: 0.0001

Data Index: 285926 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6958. Min Act: 0.0001

Data Index: 240991 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 1.4230. Min Range: -1.4230

Max Act: 0.6630. Min Act: -0.0000

Data Index: 843525 (C4 (Web Text))

Max Activating Token Index: 802