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

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

Neuron 3887 in Layer 0

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: 0.5671. Min Range: -0.5671

Max Act: 0.5671. Min Act: -0.0001

Data Index: 1219757 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5293. Min Act: -0.0001

Data Index: 1406616 (Python Code)

Max Activating Token Index: 1019

Text #2

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5302. Min Act: -0.0001

Data Index: 1470813 (Python Code)

Max Activating Token Index: 893

Text #3

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5025. Min Act: -0.0001

Data Index: 106112 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.5079. Min Act: -0.0001

Data Index: 1428074 (Python Code)

Max Activating Token Index: 993

Text #5

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4990. Min Act: -0.0001

Data Index: 334131 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1414946 (Python Code)

Max Activating Token Index: 910

Text #7

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4921. Min Act: -0.0001

Data Index: 1454165 (Python Code)

Max Activating Token Index: 135

Text #8

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4925. Min Act: -0.0001

Data Index: 1216532 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4762. Min Act: -0.0001

Data Index: 740268 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4928. Min Act: -0.0001

Data Index: 276036 (C4 (Web Text))

Max Activating Token Index: 407

Text #11

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4811. Min Act: -0.0001

Data Index: 1495667 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4738. Min Act: -0.0001

Data Index: 1049336 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4819. Min Act: -0.0001

Data Index: 1655493 (Python Code)

Max Activating Token Index: 990

Text #14

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4835. Min Act: -0.0001

Data Index: 67208 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4705. Min Act: -0.0001

Data Index: 450988 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4667. Min Act: -0.0001

Data Index: 1245158 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4791. Min Act: -0.0001

Data Index: 1373992 (Python Code)

Max Activating Token Index: 917

Text #18

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4612. Min Act: -0.0001

Data Index: 603247 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.5671. Min Range: -0.5671

Max Act: 0.4587. Min Act: -0.0001

Data Index: 601803 (C4 (Web Text))

Max Activating Token Index: 1014