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

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

Neuron 3224 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.8476. Min Act: -0.0000

Data Index: 1292682 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6985. Min Act: -0.0000

Data Index: 934274 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.7667. Min Act: -0.0000

Data Index: 877849 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.6395. Min Act: -0.0000

Data Index: 1132017 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5830. Min Act: -0.0000

Data Index: 389466 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5694. Min Act: -0.0000

Data Index: 294766 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5189. Min Act: -0.0000

Data Index: 807844 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4238. Min Act: -0.0000

Data Index: 1213074 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5028. Min Act: -0.0000

Data Index: 746751 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3681. Min Act: -0.0000

Data Index: 1005272 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4076. Min Act: -0.0000

Data Index: 6573 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.4108. Min Act: -0.0000

Data Index: 521860 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1296952 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3795. Min Act: -0.0000

Data Index: 1117791 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3677. Min Act: -0.0000

Data Index: 1302852 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1046935 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3246. Min Act: -0.0000

Data Index: 737435 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3476. Min Act: -0.0000

Data Index: 422860 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3365. Min Act: -0.0000

Data Index: 1359775 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2746. Min Act: -0.0000

Data Index: 1164998 (C4 (Web Text))

Max Activating Token Index: 709