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

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

Neuron 1015 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: 4.9419. Min Range: -4.9419

Max Act: 4.9419. Min Act: -0.0001

Data Index: 1270008 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 4.9419. Min Range: -4.9419

Max Act: 4.0198. Min Act: -0.0001

Data Index: 300419 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.6675. Min Act: -0.0001

Data Index: 168999 (C4 (Web Text))

Max Activating Token Index: 448

Text #3

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.8022. Min Act: -0.0001

Data Index: 1200768 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.9554. Min Act: -0.0001

Data Index: 658919 (C4 (Web Text))

Max Activating Token Index: 767

Text #5

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.7941. Min Act: -0.0001

Data Index: 278002 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.7413. Min Act: -0.0001

Data Index: 791852 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.4491. Min Act: -0.0001

Data Index: 159681 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.6763. Min Act: -0.0001

Data Index: 1258088 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.6787. Min Act: -0.0001

Data Index: 891705 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.5060. Min Act: -0.0001

Data Index: 493804 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.4857. Min Act: -0.0001

Data Index: 679091 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.5981. Min Act: -0.0001

Data Index: 953659 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.3870. Min Act: -0.0001

Data Index: 291983 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.3743. Min Act: -0.0001

Data Index: 282869 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.3515. Min Act: -0.0001

Data Index: 640676 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.2904. Min Act: -0.0001

Data Index: 773010 (C4 (Web Text))

Max Activating Token Index: 254

Text #17

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.2482. Min Act: -0.0001

Data Index: 691017 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.3408. Min Act: -0.0001

Data Index: 121224 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 4.9419. Min Range: -4.9419

Max Act: 3.4787. Min Act: -0.0001

Data Index: 1233238 (C4 (Web Text))

Max Activating Token Index: 791