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

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

Neuron 1159 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0272. Min Range: -1.0272

Max Act: 1.0272. Min Act: -0.0001

Data Index: 1187768 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7932. Min Act: -0.0001

Data Index: 847002 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8075. Min Act: -0.0001

Data Index: 1088203 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.8047. Min Act: -0.0001

Data Index: 454555 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7689. Min Act: -0.0001

Data Index: 248731 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6954. Min Act: -0.0001

Data Index: 462050 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1293271 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7380. Min Act: -0.0001

Data Index: 1188567 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7306. Min Act: -0.0001

Data Index: 896851 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7015. Min Act: -0.0001

Data Index: 93639 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7448. Min Act: -0.0001

Data Index: 884898 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6976. Min Act: -0.0001

Data Index: 989699 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7234. Min Act: -0.0001

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7019. Min Act: -0.0001

Data Index: 1163513 (C4 (Web Text))

Max Activating Token Index: 437

Text #14

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1178731 (C4 (Web Text))

Max Activating Token Index: 412

Text #15

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7193. Min Act: -0.0001

Data Index: 334233 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6932. Min Act: -0.0001

Data Index: 1021520 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7056. Min Act: -0.0001

Data Index: 307417 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.6833. Min Act: -0.0001

Data Index: 538774 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.0272. Min Range: -1.0272

Max Act: 0.7018. Min Act: -0.0001

Data Index: 205774 (C4 (Web Text))

Max Activating Token Index: 963