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

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

Neuron 2682 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.2603. Min Act: -0.0000

Data Index: 689819 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.3495. Min Act: -0.0000

Data Index: 859345 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.3380. Min Act: -0.0000

Data Index: 1317324 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.4131. Min Act: -0.0000

Data Index: 814147 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.8327. Min Act: -0.0000

Data Index: 1217120 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.2561. Min Act: -0.0000

Data Index: 177833 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.7933. Min Act: -0.0000

Data Index: 69606 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.2268. Min Act: -0.0000

Data Index: 1138711 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.0750. Min Act: -0.0000

Data Index: 433635 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 2.7933. Min Range: -2.7933

Max Act: 2.1305. Min Act: -0.0000

Data Index: 1136179 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1110710 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.9198. Min Act: -0.0000

Data Index: 1233739 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.9259. Min Act: -0.0000

Data Index: 91774 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1335116 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.7997. Min Act: -0.0000

Data Index: 810018 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.8721. Min Act: -0.0000

Data Index: 124287 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.8925. Min Act: -0.0000

Data Index: 957653 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.7352. Min Act: -0.0000

Data Index: 807418 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.7026. Min Act: -0.0000

Data Index: 493256 (C4 (Web Text))

Max Activating Token Index: 506

Text #19

Max Range: 2.7933. Min Range: -2.7933

Max Act: 1.8022. Min Act: -0.0000

Data Index: 315949 (C4 (Web Text))

Max Activating Token Index: 905