Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 291 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.3520. Min Act: -0.0000

Data Index: 34226 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.2139. Min Act: -0.0000

Data Index: 190152 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.1009. Min Act: -0.0001

Data Index: 29903 (C4 (Web Text))

Max Activating Token Index: 293

Text #3

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0788. Min Act: -0.0000

Data Index: 384788 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1344349 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0323. Min Act: -0.0001

Data Index: 504711 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9862. Min Act: -0.0000

Data Index: 555634 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0020. Min Act: -0.0001

Data Index: 351199 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1232478 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0854. Min Act: -0.0001

Data Index: 1312351 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 1.3520. Min Range: -1.3520

Max Act: 1.0599. Min Act: -0.0001

Data Index: 1009649 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1006365 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9108. Min Act: -0.0001

Data Index: 32903 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.9164. Min Act: -0.0000

Data Index: 436827 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8338. Min Act: -0.0000

Data Index: 877134 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8345. Min Act: -0.0000

Data Index: 588023 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8494. Min Act: -0.0000

Data Index: 97985 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1119748 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8501. Min Act: -0.0001

Data Index: 1047323 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.3520. Min Range: -1.3520

Max Act: 0.8037. Min Act: -0.0001

Data Index: 786236 (C4 (Web Text))

Max Activating Token Index: 433