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

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

Neuron 813 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: 1.5909. Min Range: -1.5909

Max Act: 1.5909. Min Act: -0.0002

Data Index: 1312490 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4445. Min Act: -0.0002

Data Index: 171958 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4226. Min Act: -0.0002

Data Index: 266960 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4225. Min Act: -0.0002

Data Index: 1270646 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4218. Min Act: -0.0002

Data Index: 333240 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3968. Min Act: -0.0002

Data Index: 1356076 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.4178. Min Act: -0.0002

Data Index: 450657 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3688. Min Act: -0.0002

Data Index: 818874 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3713. Min Act: -0.0002

Data Index: 346673 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3574. Min Act: -0.0002

Data Index: 350050 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3501. Min Act: -0.0002

Data Index: 815430 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3570. Min Act: -0.0002

Data Index: 782936 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3620. Min Act: -0.0002

Data Index: 453766 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3509. Min Act: -0.0002

Data Index: 35718 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3051. Min Act: -0.0002

Data Index: 379321 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3069. Min Act: -0.0002

Data Index: 502153 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3325. Min Act: -0.0002

Data Index: 1302815 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3021. Min Act: -0.0002

Data Index: 534704 (C4 (Web Text))

Max Activating Token Index: 137

Text #18

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2964. Min Act: -0.0002

Data Index: 1158285 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.3167. Min Act: -0.0002

Data Index: 232567 (C4 (Web Text))

Max Activating Token Index: 54