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

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

Neuron 1371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1115591 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.2887. Min Act: -0.0000

Data Index: 1357415 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.3140. Min Act: -0.0000

Data Index: 1120255 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.2357. Min Act: -0.0001

Data Index: 120778 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.1874. Min Act: -0.0000

Data Index: 414124 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.1601. Min Act: -0.0000

Data Index: 876244 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.1056. Min Act: -0.0000

Data Index: 308450 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0356. Min Act: -0.0000

Data Index: 1123026 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0615. Min Act: -0.0000

Data Index: 438816 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0468. Min Act: -0.0000

Data Index: 104757 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0251. Min Act: -0.0000

Data Index: 278593 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0506. Min Act: -0.0000

Data Index: 663757 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0723. Min Act: -0.0000

Data Index: 50606 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1324940 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 1.3140. Min Range: -1.3140

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1151138 (C4 (Web Text))

Max Activating Token Index: 1008

Text #15

Max Range: 1.3140. Min Range: -1.3140

Max Act: 0.9527. Min Act: -0.0001

Data Index: 893162 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 1.3140. Min Range: -1.3140

Max Act: 0.9567. Min Act: -0.0001

Data Index: 958314 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 1.3140. Min Range: -1.3140

Max Act: 0.9385. Min Act: -0.0000

Data Index: 609989 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 1.3140. Min Range: -1.3140

Max Act: 0.9301. Min Act: -0.0000

Data Index: 212482 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 1.3140. Min Range: -1.3140

Max Act: 0.9853. Min Act: -0.0000

Data Index: 142620 (C4 (Web Text))

Max Activating Token Index: 146