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

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

Neuron 6004 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1317502 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.5578. Min Act: -0.0000

Data Index: 388277 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.3245. Min Act: -0.0000

Data Index: 1092470 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.3156. Min Act: -0.0000

Data Index: 418912 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.1253. Min Act: -0.0000

Data Index: 698446 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9725. Min Act: -0.0000

Data Index: 796913 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9334. Min Act: -0.0000

Data Index: 1283266 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9524. Min Act: -0.0000

Data Index: 697852 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9636. Min Act: -0.0000

Data Index: 1285961 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8442. Min Act: -0.0000

Data Index: 802832 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9095. Min Act: -0.0000

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 2.5962. Min Range: -2.5962

Max Act: 2.0340. Min Act: -0.0000

Data Index: 1071516 (C4 (Web Text))

Max Activating Token Index: 426

Text #12

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8954. Min Act: -0.0000

Data Index: 897574 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.9110. Min Act: -0.0000

Data Index: 42362 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8859. Min Act: -0.0000

Data Index: 274413 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8699. Min Act: -0.0000

Data Index: 5887 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8726. Min Act: -0.0000

Data Index: 684118 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8648. Min Act: -0.0000

Data Index: 122734 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8456. Min Act: -0.0000

Data Index: 732103 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 2.5962. Min Range: -2.5962

Max Act: 1.8137. Min Act: -0.0000

Data Index: 1009516 (C4 (Web Text))

Max Activating Token Index: 68