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

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

Neuron 586 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: 0.4385. Min Range: -0.4385

Max Act: 0.4385. Min Act: -0.0001

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4324. Min Act: -0.0001

Data Index: 43812 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4163. Min Act: -0.0001

Data Index: 745978 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4209. Min Act: -0.0001

Data Index: 934529 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4248. Min Act: -0.0001

Data Index: 833576 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4085. Min Act: -0.0001

Data Index: 336038 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4124. Min Act: -0.0001

Data Index: 891080 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4105. Min Act: -0.0001

Data Index: 34534 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4097. Min Act: -0.0001

Data Index: 112951 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4084. Min Act: -0.0001

Data Index: 1013168 (C4 (Web Text))

Max Activating Token Index: 141

Text #10

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.4009. Min Act: -0.0001

Data Index: 882945 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3969. Min Act: -0.0001

Data Index: 880719 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3949. Min Act: -0.0001

Data Index: 146595 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3949. Min Act: -0.0001

Data Index: 1355767 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1228288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3996. Min Act: -0.0001

Data Index: 38285 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3955. Min Act: -0.0001

Data Index: 868674 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3966. Min Act: -0.0001

Data Index: 828133 (C4 (Web Text))

Max Activating Token Index: 6

Text #18

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3883. Min Act: -0.0001

Data Index: 667802 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.4385. Min Range: -0.4385

Max Act: 0.3961. Min Act: -0.0001

Data Index: 1223900 (C4 (Web Text))

Max Activating Token Index: 805