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

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

Neuron 3424 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4232. Min Range: -2.4232

Max Act: 2.4232. Min Act: -0.0000

Data Index: 237646 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.8428. Min Act: -0.0000

Data Index: 847166 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.9976. Min Act: -0.0000

Data Index: 190400 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 2.4232. Min Range: -2.4232

Max Act: 2.0187. Min Act: -0.0000

Data Index: 140355 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.8612. Min Act: -0.0000

Data Index: 997570 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.6261. Min Act: -0.0000

Data Index: 43714 (C4 (Web Text))

Max Activating Token Index: 561

Text #6

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1228270 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.4532. Min Act: -0.0000

Data Index: 925944 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.5872. Min Act: -0.0000

Data Index: 1124352 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.5862. Min Act: -0.0000

Data Index: 1091873 (C4 (Web Text))

Max Activating Token Index: 57

Text #10

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.2504. Min Act: -0.0000

Data Index: 686242 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.4445. Min Act: -0.0000

Data Index: 492806 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.2459. Min Act: -0.0000

Data Index: 118590 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.5037. Min Act: -0.0000

Data Index: 1143952 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.3731. Min Act: -0.0000

Data Index: 758758 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1169546 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1067680 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.3149. Min Act: -0.0000

Data Index: 453329 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.2390. Min Act: -0.0000

Data Index: 301117 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 2.4232. Min Range: -2.4232

Max Act: 1.2340. Min Act: -0.0000

Data Index: 405668 (C4 (Web Text))

Max Activating Token Index: 958