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

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

Neuron 5410 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: 1.0576. Min Range: -1.0576

Max Act: 1.0576. Min Act: -0.0002

Data Index: 1335805 (C4 (Web Text))

Max Activating Token Index: 61

Text #1

Max Range: 1.0576. Min Range: -1.0576

Max Act: 1.0164. Min Act: -0.0002

Data Index: 611654 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9615. Min Act: -0.0002

Data Index: 723478 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9694. Min Act: -0.0002

Data Index: 556873 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9586. Min Act: -0.0002

Data Index: 1133208 (C4 (Web Text))

Max Activating Token Index: 505

Text #5

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9284. Min Act: -0.0002

Data Index: 69819 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9289. Min Act: -0.0002

Data Index: 463025 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9357. Min Act: -0.0002

Data Index: 888770 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8921. Min Act: -0.0002

Data Index: 1213036 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9031. Min Act: -0.0002

Data Index: 453581 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8841. Min Act: -0.0002

Data Index: 592705 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9066. Min Act: -0.0002

Data Index: 33824 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9029. Min Act: -0.0002

Data Index: 1339260 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8818. Min Act: -0.0002

Data Index: 334709 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8480. Min Act: -0.0002

Data Index: 546815 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8757. Min Act: -0.0002

Data Index: 115780 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.9057. Min Act: -0.0002

Data Index: 1301311 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8757. Min Act: -0.0002

Data Index: 442509 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8890. Min Act: -0.0002

Data Index: 1249166 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.0576. Min Range: -1.0576

Max Act: 0.8602. Min Act: -0.0002

Data Index: 503681 (C4 (Web Text))

Max Activating Token Index: 7