Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 15 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.8632. Min Act: -0.0001

Data Index: 857362 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.3802. Min Act: -0.0001

Data Index: 499013 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.5327. Min Act: -0.0001

Data Index: 200012 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.2287. Min Act: -0.0001

Data Index: 1096399 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.7725. Min Act: -0.0001

Data Index: 552661 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.1145. Min Act: -0.0001

Data Index: 1148734 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.4241. Min Act: -0.0001

Data Index: 634594 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.7748. Min Act: -0.0001

Data Index: 273004 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.5930. Min Act: -0.0001

Data Index: 1236380 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.5893. Min Act: -0.0001

Data Index: 592368 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 5.8632. Min Range: -5.8632

Max Act: 5.0230. Min Act: -0.0001

Data Index: 1079701 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.6415. Min Act: -0.0001

Data Index: 550646 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.3112. Min Act: -0.0001

Data Index: 1342138 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.4453. Min Act: -0.0001

Data Index: 1080901 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.4430. Min Act: -0.0001

Data Index: 82009 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.7383. Min Act: -0.0001

Data Index: 921411 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.3636. Min Act: -0.0001

Data Index: 546922 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.5148. Min Act: -0.0001

Data Index: 394738 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.2953. Min Act: -0.0001

Data Index: 1136241 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 5.8632. Min Range: -5.8632

Max Act: 4.3146. Min Act: -0.0001

Data Index: 872561 (C4 (Web Text))

Max Activating Token Index: 742