Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2317 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0004

Data Index: 100718 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0569. Min Act: -0.0004

Data Index: 1164481 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0528. Min Act: -0.0004

Data Index: 313356 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0476. Min Act: -0.0004

Data Index: 697271 (C4 (Web Text))

Max Activating Token Index: 923

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0505. Min Act: -0.0004

Data Index: 960729 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0501. Min Act: -0.0004

Data Index: 514143 (C4 (Web Text))

Max Activating Token Index: 163

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0443. Min Act: -0.0004

Data Index: 429378 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0472. Min Act: -0.0004

Data Index: 829158 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0452. Min Act: -0.0004

Data Index: 12913 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0454. Min Act: -0.0004

Data Index: 1042784 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0450. Min Act: -0.0004

Data Index: 322986 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0430. Min Act: -0.0004

Data Index: 473377 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0448. Min Act: -0.0004

Data Index: 864687 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0449. Min Act: -0.0004

Data Index: 388261 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0445. Min Act: -0.0004

Data Index: 670087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0463. Min Act: -0.0004

Data Index: 127275 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0504. Min Act: -0.0004

Data Index: 99768 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0406. Min Act: -0.0004

Data Index: 1357403 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0440. Min Act: -0.0004

Data Index: 20440 (C4 (Web Text))

Max Activating Token Index: 184

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0422. Min Act: -0.0004

Data Index: 1204294 (C4 (Web Text))

Max Activating Token Index: 41