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

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

Neuron 3660 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.3193. Min Act: -0.0001

Data Index: 1231222 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1407. Min Act: -0.0001

Data Index: 123481 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.1217. Min Act: -0.0001

Data Index: 84463 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0555. Min Act: -0.0001

Data Index: 18965 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0408. Min Act: -0.0001

Data Index: 177265 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.3193. Min Range: -1.3193

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1128779 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9828. Min Act: -0.0001

Data Index: 916964 (C4 (Web Text))

Max Activating Token Index: 650

Text #7

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9585. Min Act: -0.0001

Data Index: 282821 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9780. Min Act: -0.0001

Data Index: 226343 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1161887 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9230. Min Act: -0.0001

Data Index: 1250336 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8804. Min Act: -0.0001

Data Index: 1177014 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9015. Min Act: -0.0001

Data Index: 818560 (C4 (Web Text))

Max Activating Token Index: 481

Text #13

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.9409. Min Act: -0.0001

Data Index: 728741 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8254. Min Act: -0.0001

Data Index: 817019 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8778. Min Act: -0.0001

Data Index: 783057 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8234. Min Act: -0.0001

Data Index: 783092 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8195. Min Act: -0.0001

Data Index: 804360 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8365. Min Act: -0.0001

Data Index: 989992 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 1.3193. Min Range: -1.3193

Max Act: 0.8276. Min Act: -0.0001

Data Index: 525565 (C4 (Web Text))

Max Activating Token Index: 818