Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.4198. Min Act: -0.0001

Data Index: 24642 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3991. Min Act: -0.0001

Data Index: 1032252 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3573. Min Act: -0.0001

Data Index: 1127736 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3334. Min Act: -0.0001

Data Index: 424776 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3408. Min Act: -0.0001

Data Index: 874205 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3438. Min Act: -0.0000

Data Index: 889187 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3282. Min Act: -0.0000

Data Index: 299510 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3174. Min Act: -0.0001

Data Index: 841636 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3169. Min Act: -0.0001

Data Index: 602138 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3185. Min Act: -0.0001

Data Index: 443408 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2735. Min Act: -0.0001

Data Index: 1228849 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3216. Min Act: -0.0001

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3270. Min Act: -0.0001

Data Index: 540356 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1072473 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2935. Min Act: -0.0000

Data Index: 549041 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2826. Min Act: -0.0001

Data Index: 209436 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2609. Min Act: -0.0000

Data Index: 996579 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2787. Min Act: -0.0001

Data Index: 439913 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2800. Min Act: -0.0001

Data Index: 484250 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 0.4198. Min Range: -0.4198

Max Act: 0.2822. Min Act: -0.0001

Data Index: 725420 (C4 (Web Text))

Max Activating Token Index: 847