Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3297 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0079. Min Range: -1.0079

Max Act: 1.0079. Min Act: -0.0001

Data Index: 1214275 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9644. Min Act: -0.0001

Data Index: 232655 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8827. Min Act: -0.0001

Data Index: 129233 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.9064. Min Act: -0.0001

Data Index: 277460 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8795. Min Act: -0.0001

Data Index: 528309 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7965. Min Act: -0.0001

Data Index: 639192 (C4 (Web Text))

Max Activating Token Index: 136

Text #6

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.8139. Min Act: -0.0001

Data Index: 996938 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7534. Min Act: -0.0001

Data Index: 296508 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7903. Min Act: -0.0001

Data Index: 894275 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6606. Min Act: -0.0001

Data Index: 112842 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7484. Min Act: -0.0001

Data Index: 585673 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7730. Min Act: -0.0001

Data Index: 847058 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6919. Min Act: -0.0001

Data Index: 398453 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6905. Min Act: -0.0001

Data Index: 227542 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6961. Min Act: -0.0001

Data Index: 137401 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7150. Min Act: -0.0001

Data Index: 722734 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6933. Min Act: -0.0001

Data Index: 382343 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7280. Min Act: -0.0001

Data Index: 167304 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.6437. Min Act: -0.0001

Data Index: 390164 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 1.0079. Min Range: -1.0079

Max Act: 0.7966. Min Act: -0.0001

Data Index: 1095689 (C4 (Web Text))

Max Activating Token Index: 504