Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1011526 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1436. Min Act: -0.0001

Data Index: 339145 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1416. Min Act: -0.0001

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1015092 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1330. Min Act: -0.0001

Data Index: 213630 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1250. Min Act: -0.0001

Data Index: 318173 (C4 (Web Text))

Max Activating Token Index: 329

Text #6

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1213. Min Act: -0.0001

Data Index: 132497 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1288. Min Act: -0.0001

Data Index: 383644 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1280. Min Act: -0.0001

Data Index: 229745 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1220. Min Act: -0.0001

Data Index: 683390 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1270. Min Act: -0.0001

Data Index: 216109 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1256. Min Act: -0.0001

Data Index: 695 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1238643 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1201. Min Act: -0.0001

Data Index: 803895 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1234. Min Act: -0.0001

Data Index: 692329 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1288. Min Act: -0.0001

Data Index: 919398 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1233. Min Act: -0.0001

Data Index: 281824 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1287. Min Act: -0.0001

Data Index: 342940 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1182. Min Act: -0.0001

Data Index: 687119 (C4 (Web Text))

Max Activating Token Index: 902

Text #19

Max Range: 0.1436. Min Range: -0.1436

Max Act: 0.1218. Min Act: -0.0001

Data Index: 9180 (C4 (Web Text))

Max Activating Token Index: 248