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

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

Neuron 5232 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1480542 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3440. Min Act: -0.0001

Data Index: 40175 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3416. Min Act: -0.0001

Data Index: 93605 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3449. Min Act: -0.0002

Data Index: 269567 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3455. Min Act: -0.0001

Data Index: 682638 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3382. Min Act: -0.0001

Data Index: 1192122 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3283. Min Act: -0.0001

Data Index: 651351 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3215. Min Act: -0.0001

Data Index: 1045079 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3238. Min Act: -0.0001

Data Index: 893839 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3244. Min Act: -0.0001

Data Index: 632056 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3239. Min Act: -0.0001

Data Index: 915229 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3198. Min Act: -0.0001

Data Index: 250149 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3215. Min Act: -0.0001

Data Index: 409691 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3192. Min Act: -0.0002

Data Index: 1514713 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3248. Min Act: -0.0001

Data Index: 4616 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3148. Min Act: -0.0001

Data Index: 443297 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3173. Min Act: -0.0001

Data Index: 497972 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3135. Min Act: -0.0001

Data Index: 233458 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3140. Min Act: -0.0001

Data Index: 313403 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3143. Min Act: -0.0001

Data Index: 844816 (C4 (Web Text))

Max Activating Token Index: 31