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

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

Neuron 5964 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 3.1092. Min Range: -3.1092

Max Act: 3.1092. Min Act: -0.0002

Data Index: 822776 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9932. Min Act: -0.0002

Data Index: 1148423 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 3.1092. Min Range: -3.1092

Max Act: 3.0248. Min Act: -0.0002

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9792. Min Act: -0.0002

Data Index: 1028920 (C4 (Web Text))

Max Activating Token Index: 134

Text #4

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9591. Min Act: -0.0002

Data Index: 1279953 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9668. Min Act: -0.0002

Data Index: 1342693 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.9359. Min Act: -0.0002

Data Index: 430696 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8641. Min Act: -0.0002

Data Index: 939321 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8592. Min Act: -0.0002

Data Index: 473573 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8062. Min Act: -0.0002

Data Index: 1226885 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8021. Min Act: -0.0002

Data Index: 591307 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.8217. Min Act: -0.0002

Data Index: 449591 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7103. Min Act: -0.0002

Data Index: 43624 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7292. Min Act: -0.0002

Data Index: 461037 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7521. Min Act: -0.0002

Data Index: 962789 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7565. Min Act: -0.0002

Data Index: 622118 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7102. Min Act: -0.0002

Data Index: 461441 (C4 (Web Text))

Max Activating Token Index: 520

Text #17

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7209. Min Act: -0.0002

Data Index: 1073017 (C4 (Web Text))

Max Activating Token Index: 192

Text #18

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.6813. Min Act: -0.0002

Data Index: 447443 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 3.1092. Min Range: -3.1092

Max Act: 2.7700. Min Act: -0.0002

Data Index: 867005 (C4 (Web Text))

Max Activating Token Index: 242